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

    Neuronpedia

    INDEX
    Explanations

    Z names and algebra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Portal
    0.73
     क्विंटल
    0.73
     Current
    0.72
     Great
    0.70
    Current
    0.68
     Portable
    0.67
    Great
    0.67
    Strat
    0.66
     Foreground
    0.65
     Rusty
    0.65
    POSITIVE LOGITS
    ogenesis
    0.80
     venne
    0.76
     anhand
    0.72
    理
    0.70
    ahnya
    0.70
    indrical
    0.69
    aufgaben
    0.69
    OGEN
    0.69
     tooth
    0.69
    ভূ
    0.69
    Act Density 0.004%

    No Known Activations