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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کتاب
    -0.07
     ウ
    -0.07
     Estate
    -0.07
    Communic
    -0.06
    _Manager
    -0.06
    edar
    -0.06
     Dialog
    -0.06
     Giving
    -0.06
    _VALIDATE
    -0.06
    Curso
    -0.06
    POSITIVE LOGITS
    egrate
    0.06
    LayoutConstraint
    0.06
    строй
    0.06
    ös
    0.06
    nesení
    0.06
    .IOException
    0.06
    (req
    0.06
     autogenerated
    0.06
     bom
    0.05
    tip
    0.05
    Act Density 0.003%

    No Known Activations