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

    Neuronpedia

    INDEX
    Explanations

    diagnostic criteria or measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    0.52
    هش
    0.52
    l
    0.49
     brach
    0.46
    Haupt
    0.46
    h
    0.45
    تال
    0.44
    Ag
    0.44
     maxx
    0.43
     siquiera
    0.42
    POSITIVE LOGITS
     améli
    0.47
     erreurs
    0.45
     illusions
    0.45
    𝙽
    0.45
     attenuation
    0.44
    ộng
    0.44
     remnants
    0.44
     buffs
    0.44
    که
    0.43
     अंडर
    0.43
    Act Density 0.001%

    No Known Activations