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

    Neuronpedia

    INDEX
    Explanations

    load

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ["_
    -0.07
     Monte
    -0.06
     merchant
    -0.06
     quello
    -0.06
    右手
    -0.06
    _acc
    -0.06
     shin
    -0.06
    _codec
    -0.06
     misunderstanding
    -0.06
     tiếng
    -0.06
    POSITIVE LOGITS
     jealous
    0.07
    个百分点
    0.07
    时间内
    0.07
    owych
    0.07
     값
    0.07
     newPosition
    0.07
    아버
    0.07
    tat
    0.07
     Mend
    0.07
     liabilities
    0.07
    Act Density 0.000%

    No Known Activations