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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rir
    -0.75
    zech
    -0.74
    patch
    -0.74
    sylv
    -0.74
    ebus
    -0.73
    dinand
    -0.72
    ervatives
    -0.71
    Downloadha
    -0.71
    aez
    -0.70
     guiActiveUn
    -0.69
    POSITIVE LOGITS
     ML
    0.69
     Tanks
    0.68
     Kiw
    0.66
     NF
    0.65
     NAD
    0.63
     TOR
    0.63
     NAS
    0.62
     Messages
    0.62
     FC
    0.61
    arget
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.