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

    Neuronpedia

    INDEX
    Explanations

    technical terms, concepts, and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chaired
    0.45
    ᖕ
    0.43
    assertSame
    0.42
    ignée
    0.42
    gleichen
    0.42
     Combs
    0.40
    collisions
    0.40
    ض
    0.40
    atterson
    0.39
    ldon
    0.39
    POSITIVE LOGITS
     Email
    0.42
    Beta
    0.38
     Keb
    0.36
     Custom
    0.36
     Beta
    0.36
    امت
    0.36
     Umm
    0.36
    Custom
    0.36
     mening
    0.36
     Kumb
    0.35
    Act Density 0.000%

    No Known Activations