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

    Neuronpedia

    INDEX
    Explanations

    compound nouns and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     debacle
    1.41
     goma
    1.34
    ис
    1.33
    ться
    1.32
     încep
    1.32
     заход
    1.31
    菄
    1.30
     στό
    1.30
    lassen
    1.28
     remaja
    1.27
    POSITIVE LOGITS
    ally
    1.21
    蒡
    1.10
    izing
    1.07
     Jack
    1.04
    бие
    1.03
     Milan
    1.02
     Fraction
    1.00
    BOTH
    0.97
    legi
    0.96
     Turing
    0.95
    Act Density 0.001%

    No Known Activations