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

    Neuronpedia

    INDEX
    Explanations

    common phrases and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urgence
    0.46
    घे
    0.42
    ernum
    0.40
    療法
    0.39
    ṕ
    0.39
     زبان
    0.38
    영상
    0.38
    的很
    0.38
    মিনা
    0.38
    ജീവ
    0.38
    POSITIVE LOGITS
    Extreme
    0.40
    setPointSize
    0.39
    Cond
    0.37
    вале
    0.36
    (-
    0.36
     कौ
    0.36
    Mal
    0.35
     acknowledge
    0.35
    olina
    0.35
     Extreme
    0.35
    Act Density 0.000%

    No Known Activations