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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Panama
    -0.80
     Indra
    -0.77
     Mongo
    -0.74
     Salvation
    -0.73
     Admir
    -0.72
     Patron
    -0.71
     Isles
    -0.70
     Providence
    -0.66
     Halifax
    -0.65
     Polk
    -0.65
    POSITIVE LOGITS
    staking
    0.87
    ooming
    0.75
    âĺ
    0.75
     ILCS
    0.73
    rust
    0.72
    edit
    0.71
    âĨ
    0.69
    %]
    0.69
    pletion
    0.69
    metic
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.