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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     validationResult
    -0.06
    istle
    -0.06
    -stop
    -0.06
     Week
    -0.06
     retains
    -0.06
    ー�
    -0.06
    ظ
    -0.06
    igs
    -0.06
     Fi
    -0.06
     mpg
    -0.06
    POSITIVE LOGITS
     тай
    0.07
    /watch
    0.06
     размещ
    0.06
     náz
    0.06
     개최
    0.06
     ginger
    0.06
    �
    0.06
    <(),
    0.06
     бач
    0.06
     scans
    0.06
    Act Density 0.010%

    No Known Activations