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

    Neuronpedia

    INDEX
    Explanations

    "because" and "'t"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .drag
    -0.07
    ='%
    -0.07
     بیشتری
    -0.07
    .notice
    -0.06
    打开
    -0.06
    거래
    -0.06
    ("{}
    -0.06
     convers
    -0.06
     buffering
    -0.06
    ravel
    -0.06
    POSITIVE LOGITS
    (Date
    0.06
    (mb
    0.06
    (person
    0.06
     Hardware
    0.06
     precautions
    0.06
     Seahawks
    0.06
    _CASE
    0.06
    шается
    0.06
    touches
    0.06
    ยนตร
    0.05
    Act Density 0.005%

    No Known Activations