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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     You
    -0.07
     camb
    -0.06
    You
    -0.06
     emacs
    -0.06
    ţ
    -0.06
    ほう
    -0.06
     NUMBER
    -0.06
    του
    -0.06
     Manip
    -0.06
     Columns
    -0.06
    POSITIVE LOGITS
     испыт
    0.10
    within
    0.06
    dis
    0.06
    __()
    0.06
    469
    0.06
     inde
    0.06
    _pressure
    0.06
     convincing
    0.06
     علمی
    0.06
    wifi
    0.06
    Act Density 0.000%

    No Known Activations