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

    Neuronpedia

    INDEX
    Explanations

    references to climbing, ascending, or increasing

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

    ascension and descent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.53
    .*")]
    -0.51
     فريبيس
    -0.50
     endblock
    -0.50
     RemoteException
    -0.49
    WithIOException
    -0.48
     newBuilder
    -0.47
    toMatchSnapshot
    -0.45
    createStatement
    -0.45
     صوتيه
    -0.44
    POSITIVE LOGITS
     subida
    0.92
     climbing
    0.88
     climb
    0.88
     ascent
    0.84
     rise
    0.83
     montée
    0.80
     naik
    0.79
     climbs
    0.78
    Climbing
    0.76
     lên
    0.76
    Act Density 0.014%

    No Known Activations