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

    Neuronpedia

    INDEX
    Explanations

    environment or setting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pavilion
    -0.07
    .prefix
    -0.07
    iona
    -0.07
    entity
    -0.06
     Quy
    -0.06
     livro
    -0.06
    changer
    -0.06
    vana
    -0.06
    pun
    -0.06
    loyd
    -0.06
    POSITIVE LOGITS
     stricter
    0.06
    .isLoading
    0.06
     želez
    0.06
     وح
    0.06
    .builder
    0.06
    рий
    0.06
    ้
    0.06
    /security
    0.06
     يح
    0.06
    개
    0.06
    Act Density 0.093%

    No Known Activations