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

    Neuronpedia

    INDEX
    Explanations

    conditional statements expressing possibility and expectations

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

    expressing hypothetical situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bewußt
    -0.60
    ientôt
    -0.56
     orejas
    -0.53
     finanzas
    -0.50
     spalle
    -0.50
     mijne
    -0.50
     flotante
    -0.49
     <<<<<<<<<<<<<<
    -0.48
     oreilles
    -0.47
     dezelve
    -0.47
    POSITIVE LOGITS
     Gabri
    0.43
     Would
    0.42
     would
    0.40
     coaching
    0.40
    NUMX
    0.40
     Dowling
    0.39
     HIP
    0.39
     Ep
    0.39
    xmlhttp
    0.39
    Would
    0.39
    Act Density 0.239%

    No Known Activations