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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    outline
    0.71
    }^*
    0.68
    ъ
    0.68
    args
    0.67
    abbr
    0.65
    there
    0.65
    Еще
    0.65
    "$
    0.63
    address
    0.63
    fadeIn
    0.63
    POSITIVE LOGITS
     headwinds
    0.79
     prohibitions
    0.77
     merely
    0.76
     loafers
    0.76
     proverb
    0.76
    guna
    0.75
     prohibition
    0.75
     atât
    0.75
     clas
    0.74
     malfunctions
    0.73
    Act Density 0.004%

    No Known Activations