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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maths
    -0.07
    Severity
    -0.07
    他們
    -0.06
    ismic
    -0.06
    ديث
    -0.06
    دام
    -0.06
     podrob
    -0.06
     удив
    -0.06
    �n
    -0.06
    felt
    -0.06
    POSITIVE LOGITS
     Survey
    0.07
    ][]
    0.06
     �
    0.06
     Picker
    0.06
     Andres
    0.06
    .Interval
    0.06
     HR
    0.06
     يج
    0.05
     Daisy
    0.05
     liberals
    0.05
    Act Density 0.013%

    No Known Activations