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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uko
    -0.07
    /kernel
    -0.06
     puppies
    -0.06
    @↵
    -0.06
    .FragmentManager
    -0.06
    Unknown
    -0.06
    *L
    -0.06
     choking
    -0.06
    ajor
    -0.06
    weekly
    -0.06
    POSITIVE LOGITS
     dismantle
    0.07
     scatter
    0.07
     Mechanical
    0.06
    Filter
    0.06
    returnValue
    0.06
    ้าย
    0.06
    Tw
    0.06
     فناوری
    0.06
     Splash
    0.06
     Одна
    0.06
    Act Density 0.025%

    No Known Activations