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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resist
    0.80
     becoming
    0.77
     supporting
    0.73
     growing
    0.73
    等
    0.73
    .<
    0.70
     etc
    0.70
    。。。
    0.69
    ’.
    0.69
     feelings
    0.69
    POSITIVE LOGITS
     tergantung
    1.00
    depends
    0.99
    depending
    0.97
    Depends
    0.93
     depending
    0.93
     depends
    0.92
     According
    0.90
     dependiendo
    0.90
     Depending
    0.89
    Depending
    0.88
    Act Density 0.001%

    No Known Activations