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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    に向
    -0.07
     Berk
    -0.07
    �
    -0.06
    _history
    -0.06
     Friendship
    -0.06
     каз
    -0.06
     Glover
    -0.06
    ynchronized
    -0.06
    Recording
    -0.06
     infographic
    -0.06
    POSITIVE LOGITS
    Super
    0.07
    _non
    0.06
    dirty
    0.06
     //$
    0.06
     már
    0.06
     adopts
    0.06
    =sc
    0.06
     españ
    0.06
     nf
    0.06
    _fe
    0.06
    Act Density 0.054%

    No Known Activations