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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Glory
    -0.07
    stick
    -0.07
     Action
    -0.06
    anga
    -0.06
    endo
    -0.06
     explode
    -0.06
    -colored
    -0.06
     informações
    -0.06
    -history
    -0.06
    plies
    -0.06
    POSITIVE LOGITS
     ques
    0.07
     Leicester
    0.07
    IsUnicode
    0.06
     accompanied
    0.06
    ุทธ
    0.06
     Τι
    0.06
    ским
    0.06
     устра
    0.06
     bas
    0.06
    .defaultProps
    0.06
    Act Density 0.018%

    No Known Activations