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

    Neuronpedia

    INDEX
    Explanations

    total

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blind
    -0.07
     Copp
    -0.07
    替え
    -0.07
    .country
    -0.07
    _CLEAR
    -0.07
     Ling
    -0.07
    _READY
    -0.07
     Plum
    -0.07
     servicios
    -0.06
     subtle
    -0.06
    POSITIVE LOGITS
    𬴊
    0.07
     amacıyla
    0.07
     ware
    0.07
    时间
    0.07
    �
    0.07
    -offset
    0.06
    机械
    0.06
     iar
    0.06
    皭
    0.06
    \C
    0.06
    Act Density 0.042%

    No Known Activations