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

    Neuronpedia

    INDEX
    Explanations

    use each types or video

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    line
    0.46
    s
    0.46
    turn
    0.43
    ün
    0.43
    top
    0.42
    lar
    0.42
    hor
    0.41
    werte
    0.41
    granular
    0.40
    ler
    0.40
    POSITIVE LOGITS
     consequently
    0.49
     Koy
    0.45
     pollute
    0.44
     BNF
    0.44
     organs
    0.44
     infected
    0.43
     ecologically
    0.43
     créditos
    0.43
    LayerView
    0.43
     Sask
    0.43
    Act Density 0.002%

    No Known Activations