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

    Neuronpedia

    INDEX
    Explanations

    redirect Url

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grandiose
    0.45
     سون
    0.42
     acrylonitrile
    0.39
     chirality
    0.38
    чит
    0.38
    uszcz
    0.37
     refractory
    0.36
     scuole
    0.35
     Greenpeace
    0.35
     Milch
    0.35
    POSITIVE LOGITS
     terhadap
    0.42
     بالنسبه
    0.42
    来自于
    0.39
    ₍
    0.38
     بالنسبة
    0.38
    Specifically
    0.37
     specifically
    0.36
    િં
    0.36
     RP
    0.36
    sneak
    0.36
    Act Density 0.000%

    No Known Activations