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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     São
    -0.07
    -E
    -0.07
    ianne
    -0.07
     knowledge
    -0.06
    Living
    -0.06
    ACT
    -0.06
     disappe
    -0.06
    社群
    -0.06
    ann
    -0.06
     Devin
    -0.06
    POSITIVE LOGITS
    舱
    0.07
    航
    0.06
     stream
    0.06
    小狗
    0.06
     <",
    0.06
    >').
    0.06
     stock
    0.06
     liquor
    0.06
    meldung
    0.06
    _handlers
    0.06
    Act Density 0.003%

    No Known Activations