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

    Neuronpedia

    INDEX
    Explanations

    llm usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.77
    z
    0.73
    on
    0.71
    s
    0.71
    u
    0.70
    <0x80>
    0.67
    '),
    0.67
    า
    0.65
    сер
    0.63
    N
    0.61
    POSITIVE LOGITS
    تان
    0.57
     ഇപ്പോൾ
    0.55
     impediment
    0.55
    0.55
    釟
    0.54
    ৬
    0.53
     leverages
    0.51
     हंसी
    0.51
     precession
    0.50
     vibrations
    0.50
    Act Density 0.000%

    No Known Activations