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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sufficient
    0.79
     успе
    0.78
     Enough
    0.77
     enough
    0.75
    oir
    0.75
    coh
    0.71
    iper
    0.70
     adequate
    0.69
    piper
    0.67
     ounce
    0.67
    POSITIVE LOGITS
    Shin
    0.84
     شك
    0.80
     Josie
    0.77
    アレンジ
    0.76
     Jacq
    0.75
    Jamie
    0.74
    decoration
    0.74
     Garantie
    0.73
     pengaturan
    0.72
    จทย์
    0.71
    Act Density 0.001%

    No Known Activations