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

    Neuronpedia

    INDEX
    Explanations

    circuits and signals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [string
    -0.06
    .↵↵↵↵
    -0.06
    мента
    -0.06
    XmlElement
    -0.06
     Approach
    -0.06
    LoginPage
    -0.06
    -version
    -0.06
    }),
    -0.06
    DisplayName
    -0.06
     حال
    -0.06
    POSITIVE LOGITS
     Minority
    0.06
    ertime
    0.06
     عرب
    0.06
     erb
    0.06
    alaria
    0.06
     här
    0.06
    =="
    0.06
     perd
    0.06
     Correspond
    0.06
    ปก
    0.06
    Act Density 0.034%

    No Known Activations