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

    Neuronpedia

    INDEX
    Explanations

    IP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achi
    -0.07
    会同
    -0.07
    house
    -0.07
    /download
    -0.07
    ểm
    -0.07
     fools
    -0.07
    密
    -0.07
    有关
    -0.07
    whose
    -0.07
     prefix
    -0.07
    POSITIVE LOGITS
     NEW
    0.08
     Edited
    0.07
     torrent
    0.07
     Literal
    0.07
     construção
    0.07
    _sequences
    0.07
    חובה
    0.07
     Durant
    0.07
    filtered
    0.07
     injured
    0.07
    Act Density 0.011%

    No Known Activations