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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Specifies
    -0.09
     labelText
    -0.07
    rising
    -0.07
    .AppSettings
    -0.07
     billboard
    -0.06
     NSObject
    -0.06
     ValidationResult
    -0.06
    fullName
    -0.06
    Когда
    -0.06
    .CreateInstance
    -0.06
    POSITIVE LOGITS
    PE
    0.07
    verified
    0.06
     эти
    0.06
    -dominated
    0.06
    počet
    0.06
     Gu
    0.06
    verte
    0.06
    Gu
    0.06
     dostate
    0.06
    약
    0.06
    Act Density 0.086%

    No Known Activations