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

    Neuronpedia

    INDEX
    Explanations

    weigh the importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kane
    0.40
    Tooltip
    0.40
     thuần
    0.38
    itative
    0.38
    AspectRatio
    0.37
    nir
    0.37
     счита
    0.36
     Astral
    0.36
    іль
    0.36
     આપી
    0.36
    POSITIVE LOGITS
    وفر
    0.39
    绕
    0.38
     res
    0.38
    ВД
    0.37
    abilidad
    0.36
     reorgan
    0.36
     ス
    0.35
    kla
    0.35
    bras
    0.34
    회
    0.34
    Act Density 0.000%

    No Known Activations