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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.52
    9
    0.51
    MS
    0.49
    Т
    0.48
    8
    0.48
    बी
    0.47
    ky
    0.46
    ب
    0.46
    MOD
    0.45
     annual
    0.45
    POSITIVE LOGITS
     Mishra
    0.46
     prés
    0.45
     soff
    0.44
     Verfü
    0.43
     qubits
    0.43
     സമൂ
    0.43
     inflater
    0.42
     laminar
    0.42
     sứ
    0.41
     sàn
    0.41
    Act Density 0.006%

    No Known Activations