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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    v
    -0.59
     (
    -0.59
    ven
    -0.57
    vi
    -0.57
     K
    -0.55
     M
    -0.53
     C
    -0.53
    va
    -0.53
     S
    -0.52
    .
    -0.51
    POSITIVE LOGITS
    Autoritní
    1.07
     Jefus
    1.02
     itſelf
    0.98
    VIAF
    0.96
    kháu
    0.94
     Efq
    0.94
    IndentedString
    0.94
     Theſe
    0.94
     myſelf
    0.93
    ^(@)
    0.90
    Act Density 0.134%

    No Known Activations