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

    Neuronpedia

    INDEX
    Explanations

    code equality checks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ogan
    -0.07
    (interval
    -0.06
    NORMAL
    -0.06
     usuário
    -0.06
     مار
    -0.06
    (issue
    -0.06
    >Date
    -0.06
    ournals
    -0.06
    _children
    -0.06
     toolbox
    -0.06
    POSITIVE LOGITS
    likler
    0.06
    .deleteById
    0.06
     Scenes
    0.06
     perv
    0.06
    lessly
    0.06
    รอบ
    0.06
     Run
    0.06
     fastball
    0.06
    ันออก
    0.06
    ou
    0.06
    Act Density 0.009%

    No Known Activations