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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ']
    -0.74
    iencies
    -0.74
     Mub
    -0.72
    uve
    -0.71
    aqu
    -0.69
     plantations
    -0.68
     shrimp
    -0.64
    baugh
    -0.64
    cussion
    -0.64
     migr
    -0.63
    POSITIVE LOGITS
    SPA
    0.73
    è£ħ
    0.71
    EMA
    0.71
    çĭ
    0.67
    20439
    0.66
    Talk
    0.64
    Lex
    0.62
    Rad
    0.62
     Radar
    0.62
    Care
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.