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

    Neuronpedia

    INDEX
    Explanations

    shows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pad
    -0.07
     kost
    -0.07
    与
    -0.07
     fade
    -0.06
    ong
    -0.06
     Chan
    -0.06
     ته
    -0.06
     Ст
    -0.06
    もない
    -0.06
     Peripheral
    -0.06
    POSITIVE LOGITS
    Hardware
    0.07
    ๋
    0.07
    abbo
    0.06
    戻
    0.06
    opyright
    0.06
    DBNull
    0.06
     břez
    0.06
     Typical
    0.06
    Orientation
    0.06
    Tri
    0.06
    Act Density 0.005%

    No Known Activations