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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AU
    -0.06
     Kemp
    -0.06
     kob
    -0.06
    esco
    -0.06
     Lopez
    -0.06
    prd
    -0.06
     Filtering
    -0.06
     praž
    -0.06
    .default
    -0.06
     پاد
    -0.06
    POSITIVE LOGITS
     Someone
    0.07
     При
    0.07
     string
    0.07
     المست
    0.07
    _GAIN
    0.07
    conut
    0.06
    ()=>
    0.06
     बढ़
    0.06
    �
    0.06
    _review
    0.06
    Act Density 0.001%

    No Known Activations