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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.93
    IFT
    -0.73
    iven
    -0.72
    natureconservancy
    -0.66
    URA
    -0.65
    +(
    -0.63
    aund
    -0.62
     guards
    -0.60
    eva
    -0.59
    ^{
    -0.59
    POSITIVE LOGITS
    peak
    0.72
     Thro
    0.69
    eton
    0.68
    tical
    0.66
     Fairy
    0.66
    LIN
    0.63
    uala
    0.63
    yright
    0.63
    cially
    0.61
    LAN
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.