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

    Neuronpedia

    INDEX
    Explanations

    cool, friendly, and rediscovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அறிவியல்
    0.53
     ಹೃ
    0.52
     農
    0.51
     väga
    0.50
     funktionieren
    0.50
    ные
    0.50
     사회
    0.50
     privilégi
    0.49
     나
    0.49
     lösen
    0.49
    POSITIVE LOGITS
    Theme
    0.51
    ላት
    0.48
     रोकने
    0.48
    Widgets
    0.46
    ينا
    0.46
    Hip
    0.45
    ي
    0.44
    us
    0.44
    es
    0.43
    Spare
    0.43
    Act Density 0.000%

    No Known Activations