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

    Neuronpedia

    INDEX
    Explanations

    86 helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ->$
    0.96
    帶
    0.81
    =$
    0.80
    -$
    0.79
    ,$
    0.78
    :$
    0.73
     olmadığını
    0.73
     .$
    0.73
    带
    0.73
    ம்த
    0.73
    POSITIVE LOGITS
     App
    1.01
     Illuminate
    1.01
    App
    0.82
    Modules
    0.80
     League
    0.77
     Modules
    0.76
     Ill
    0.74
     Illumin
    0.71
     Intervention
    0.70
     illumination
    0.70
    Act Density 0.055%

    No Known Activations