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

    Neuronpedia

    INDEX
    Explanations

    book titles and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sklär
    0.60
    ಬೇವಿನ
    0.58
    merksamkeit
    0.58
     diamètre
    0.55
    pleClass
    0.55
    Strafpunkte
    0.54
    rbrakk
    0.54
    lytres
    0.54
    leValue
    0.54
    鸪
    0.53
    POSITIVE LOGITS
     I
    0.77
     A
    0.76
     S
    0.74
    ,
    0.74
     B
    0.70
    :
    0.69
    0.67
     T
    0.66
     P
    0.66
     or
    0.66
    Act Density 0.004%

    No Known Activations