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

    Neuronpedia

    INDEX
    Explanations

    start small, paper trade

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matcha
    0.85
     cognac
    0.84
     Krit
    0.82
     moldings
    0.80
     Weiter
    0.80
     powdery
    0.79
     ReactNative
    0.79
    маты
    0.77
    いたり
    0.77
    шы
    0.75
    POSITIVE LOGITS
    fly
    0.84
    aw
    0.82
     separado
    0.81
     pasada
    0.80
    first
    0.78
    ifornia
    0.76
    design
    0.74
    frames
    0.74
     presc
    0.74
    watching
    0.73
    Act Density 0.000%

    No Known Activations