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

    Neuronpedia

    INDEX
    Explanations

    Enhance opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.53
    е
    0.50
    ше
    0.49
    あらゆる
    0.49
    ৬
    0.49
    ρ
    0.46
     অন্তত
    0.45
     and
    0.44
     laissez
    0.44
    이지만
    0.44
    POSITIVE LOGITS
     पो
    0.41
    I
    0.41
    ↵↵
    0.40
    ot
    0.38
    ený
    0.36
     ín
    0.36
    Crisis
    0.36
    chemia
    0.35
    the
    0.35
    Calculate
    0.35
    Act Density 0.000%

    No Known Activations