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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms

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

    aspiring or past roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.60
     snippetHide
    -0.57
     tarko
    -0.56
    alakip
    -0.54
    ientras
    -0.51
    ulongan
    -0.49
    jaqueta
    -0.49
    lámpara
    -0.48
     programação
    -0.48
     lenker
    -0.47
    POSITIVE LOGITS
     aspiring
    0.61
     wanna
    0.55
     Prospective
    0.55
     Future
    0.52
     putative
    0.52
    ToBe
    0.52
     бъде
    0.51
     aspirant
    0.51
     prospective
    0.49
     future
    0.48
    Act Density 0.008%

    No Known Activations