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

    Neuronpedia

    INDEX
    Explanations

    negative states or deficiencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ie
    0.94
    aya
    0.91
    ٠
    0.91
    manship
    0.86
    iti
    0.84
    ができる
    0.84
    onde
    0.81
    ina
    0.80
     was
    0.80
    éges
    0.80
    POSITIVE LOGITS
    т
    0.96
    ভাবে
    0.91
     б
    0.90
    к
    0.83
    ิศ
    0.81
     डायरेक्टली
    0.81
    ット
    0.80
     INSPIRE
    0.79
     pétales
    0.78
     Average
    0.77
    Act Density 0.714%

    No Known Activations