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

    Neuronpedia

    INDEX
    Explanations

    predictive modeling or maintenance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.52
    ,
    0.48
     élevée
    0.47
    "]
    0.46
    Τ
    0.46
    \"]
    0.44
    ,$$
    0.43
     Estimate
    0.43
     Locals
    0.43
    緎
    0.43
    POSITIVE LOGITS
     टाक्या
    0.52
    ដល់
    0.47
    Francis
    0.47
    OutSize
    0.46
    ོ་
    0.45
    利亚
    0.44
    ろ
    0.44
    ębior
    0.44
    pois
    0.44
     Роман
    0.44
    Act Density 0.000%

    No Known Activations