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

    Neuronpedia

    INDEX
    Explanations

    knots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λα
    -0.07
    几乎
    -0.07
     ｲ
    -0.07
    ющую
    -0.07
     striving
    -0.06
     gle
    -0.06
    _sb
    -0.06
    XPath
    -0.06
    $x
    -0.06
     eoq
    -0.06
    POSITIVE LOGITS
    (firstName
    0.07
     Crazy
    0.07
     fırsat
    0.06
    (bind
    0.06
    (KERN
    0.06
    Captain
    0.06
     RequestOptions
    0.06
    이비
    0.06
    _NEW
    0.06
    친
    0.06
    Act Density 0.037%

    No Known Activations