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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Рад
    -0.07
    <n
    -0.06
    Flight
    -0.06
    Each
    -0.06
     önceki
    -0.06
     enemies
    -0.06
     unos
    -0.06
     neighbouring
    -0.06
     Πρό
    -0.06
    -x
    -0.06
    POSITIVE LOGITS
    assist
    0.07
    nocení
    0.07
     defect
    0.06
    unj
    0.06
    暂
    0.06
    .transport
    0.06
    borah
    0.06
    ureen
    0.06
     بإ
    0.06
    ±ظ
    0.06
    Act Density 0.047%

    No Known Activations