Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to presence and existence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following a verb "to be" (was, is, are, be, been)

    np_acts-logits-general · gemini-2.0-flash

    state of being or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.59
     esternos
    -0.59
     jspb
    -0.55
    GenerationType
    -0.55
    migrationBuilder
    -0.55
    Rhestr
    -0.51
     disambiguazione
    -0.51
     esboço
    -0.49
    })));
    -0.48
     defaultstate
    -0.48
    POSITIVE LOGITS
     around
    0.83
     aboard
    0.83
     abroad
    0.83
     onstage
    0.80
     in
    0.80
     here
    0.79
     inside
    0.77
     draußen
    0.77
     sitting
    0.75
     onsite
    0.75
    Act Density 0.327%

    No Known Activations