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

    Neuronpedia

    INDEX
    Explanations

    actress

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     math
    -0.07
     alert
    -0.07
    @click
    -0.07
    WithTitle
    -0.07
     בהת
    -0.07
    —"
    -0.07
    向け
    -0.06
     reducer
    -0.06
     economic
    -0.06
     dile
    -0.06
    POSITIVE LOGITS
    roring
    0.07
     услуги
    0.07
    _PERSON
    0.06
    -confidence
    0.06
     encaps
    0.06
    Χ
    0.06
    Authorize
    0.06
     شهر
    0.06
    /sidebar
    0.06
    .Factory
    0.06
    Act Density 0.010%

    No Known Activations