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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gün
    -0.07
     rehears
    -0.06
    CID
    -0.06
     regiment
    -0.06
    _tim
    -0.06
    alım
    -0.06
     ellas
    -0.06
     llam
    -0.06
    ArrayList
    -0.06
     Goodman
    -0.06
    POSITIVE LOGITS
    출
    0.07
     �
    0.07
    エ
    0.07
     公
    0.07
     통해
    0.07
     Mare
    0.07
     Dund
    0.07
    των
    0.07
    /environment
    0.07
    それ
    0.06
    Act Density 0.001%

    No Known Activations