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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pal
    -0.07
    Pay
    -0.07
    NAV
    -0.06
    on
    -0.06
    setLabel
    -0.06
    Keyword
    -0.06
    getValue
    -0.06
    _children
    -0.06
    Usu
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    asuring
    0.07
     increasingly
    0.07
    .SelectedIndex
    0.06
    �
    0.06
    뷰
    0.06
     человека
    0.06
    .Stderr
    0.06
    ategor
    0.06
     كيل
    0.06
    _FAILURE
    0.06
    Act Density 0.002%

    No Known Activations