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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peters
    -0.07
     Bog
    -0.07
    ículo
    -0.06
    -sk
    -0.06
     Fry
    -0.06
    cm
    -0.06
     destinations
    -0.06
     cans
    -0.06
    oles
    -0.06
    ，上
    -0.06
    POSITIVE LOGITS
    _Source
    0.07
    _average
    0.07
    createFrom
    0.07
     меж
    0.06
    _speed
    0.06
    러리
    0.06
    权限
    0.06
     použit
    0.06
    _extract
    0.06
     pct
    0.06
    Act Density 0.002%

    No Known Activations