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

    Neuronpedia

    INDEX
    Explanations

    instructions for software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     その他
    -0.07
     Het
    -0.07
    Alexander
    -0.06
     axial
    -0.06
     ><
    -0.06
    もっと
    -0.06
     Meredith
    -0.06
    istogram
    -0.06
     Called
    -0.06
    Amb
    -0.06
    POSITIVE LOGITS
     πάνω
    0.07
    _Selection
    0.07
     Deserialize
    0.06
     tenure
    0.06
    DATE
    0.06
    _STORAGE
    0.06
    _FAMILY
    0.06
    _pet
    0.06
     cocos
    0.06
     gö
    0.06
    Act Density 0.027%

    No Known Activations