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

    Neuronpedia

    INDEX
    Explanations

    displacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    呼
    -0.07
    'utilisation
    -0.07
    ้าก
    -0.07
     Παν
    -0.06
    ------------↵
    -0.06
     achter
    -0.06
     chefs
    -0.06
    ikal
    -0.06
    říz
    -0.06
     zá
    -0.06
    POSITIVE LOGITS
    NN
    0.07
    @synthesize
    0.07
    =tf
    0.06
     AMAZ
    0.06
    $action
    0.06
    Processing
    0.06
    HY
    0.06
    phot
    0.06
    ollywood
    0.06
    toContain
    0.05
    Act Density 0.016%

    No Known Activations