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

    Neuronpedia

    INDEX
    Explanations

    code, organizations, people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getClass
    -0.06
     Wolf
    -0.06
    くの
    -0.06
     devuelve
    -0.06
     günlük
    -0.06
     konusu
    -0.06
    Portal
    -0.06
    WM
    -0.06
    antom
    -0.06
     Gingrich
    -0.06
    POSITIVE LOGITS
    .Pattern
    0.07
     пози
    0.07
    AnimationsModule
    0.06
    行
    0.06
    ror
    0.06
    ANCED
    0.06
     nodeList
    0.06
    ाए
    0.06
     ----------------------------------------------------------------------↵
    0.06
     multic
    0.06
    Act Density 0.016%

    No Known Activations