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

    Neuronpedia

    INDEX
    Explanations

    bot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lockdown
    -0.07
     limbs
    -0.07
    具
    -0.06
    owards
    -0.06
    ufficient
    -0.06
     Quite
    -0.06
     influenza
    -0.06
    November
    -0.06
    자료
    -0.06
    aus
    -0.06
    POSITIVE LOGITS
     emoc
    0.07
     сек
    0.07
     وجه
    0.07
    _codegen
    0.06
     �
    0.06
    InnerHTML
    0.06
    _LIGHT
    0.06
     سع
    0.06
     Что
    0.06
     GRAPH
    0.06
    Act Density 0.001%

    No Known Activations