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

    Neuronpedia

    INDEX
    Explanations

    Dialogue/Quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commands
    -0.07
    'ai
    -0.07
    ongoose
    -0.07
     Avenue
    -0.07
     spotted
    -0.06
     ib
    -0.06
    ovíd
    -0.06
     dust
    -0.06
    Ya
    -0.06
     etter
    -0.06
    POSITIVE LOGITS
    !!!!
    0.07
    _FIX
    0.07
    ,this
    0.06
    ؟↵
    0.06
    μιο
    0.06
    __).
    0.06
    慌
    0.06
    ************
    0.06
    odings
    0.06
    CallableWrapper
    0.06
    Act Density 0.012%

    No Known Activations