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

    Neuronpedia

    INDEX
    Explanations

    unexpected behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idda
    -0.09
     hurdles
    -0.08
     redevelopment
    -0.08
     dared
    -0.08
     immers
    -0.08
    رم
    -0.07
     atl
    -0.07
     নিব
    -0.07
    র্ত
    -0.07
     chic
    -0.07
    POSITIVE LOGITS
     поведения
    0.12
     Verhalten
    0.12
     behaved
    0.12
     comportement
    0.12
     correctness
    0.12
     behavior
    0.12
     behaviour
    0.12
     behave
    0.11
     আচ
    0.11
     comportamento
    0.11
    Act Density 0.030%

    No Known Activations