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

    Neuronpedia

    INDEX
    Explanations

    compensation, feedback, reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    忽略
    0.92
    ဴ
    0.89
    Settl
    0.83
    ಿಸಿದ್ದರು
    0.81
     gezien
    0.80
    考慮
    0.78
    ць
    0.77
     abstracted
    0.77
     رہیں
    0.76
    bsite
    0.76
    POSITIVE LOGITS
    IA
    0.73
    Line
    0.72
    Master
    0.69
    Low
    0.69
     Lav
    0.68
     LA
    0.67
     Ferr
    0.67
     Master
    0.66
    小小
    0.66
     I
    0.65
    Act Density 0.000%

    No Known Activations