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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atche
    -0.75
    ickr
    -0.75
    jriwal
    -0.72
    iblings
    -0.72
    olitan
    -0.70
    ansky
    -0.70
    leck
    -0.67
    hops
    -0.67
    gow
    -0.67
    chell
    -0.66
    POSITIVE LOGITS
    stellar
    0.72
    Reloaded
    0.67
    Earth
    0.66
    icons
    0.65
    æĥ
    0.65
    IFIED
    0.65
    Planet
    0.63
    âĸ¬
    0.63
    Boss
    0.62
    Blocks
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.