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

    Neuronpedia

    INDEX
    Explanations

    AI, Pink, cottage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bright
    0.84
    Pend
    0.78
    Mark
    0.77
    Leg
    0.73
    Mand
    0.72
    Pink
    0.71
    ButtonClick
    0.68
    Kenn
    0.68
    Penalty
    0.68
    Amber
    0.67
    POSITIVE LOGITS
     cambiamento
    0.86
    CTIONS
    0.85
    CON
    0.84
     préférences
    0.84
    극
    0.78
    avy
    0.76
    asers
    0.76
     продукт
    0.76
     федера
    0.74
     pedibus
    0.74
    Act Density 0.001%

    No Known Activations