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

    Neuronpedia

    INDEX
    Explanations

    current form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     досто
    0.39
    Episode
    0.38
    Malcolm
    0.38
     পোষণ
    0.37
    bcd
    0.36
    Id
    0.36
    ക്കാ
    0.36
    Stress
    0.35
     образование
    0.35
    lestage
    0.35
    POSITIVE LOGITS
     form
    0.86
     sharpness
    0.80
     fitness
    0.72
    form
    0.67
     firing
    0.66
     peak
    0.66
     sharp
    0.66
     shape
    0.63
    Firing
    0.63
     condition
    0.61
    Act Density 0.014%

    No Known Activations