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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laundry
    -0.08
     tert
    -0.07
     repeated
    -0.06
     courageous
    -0.06
     能
    -0.06
     brief
    -0.06
    템
    -0.06
    -learning
    -0.06
    フレ
    -0.06
    خم
    -0.06
    POSITIVE LOGITS
     ACPI
    0.07
    IMO
    0.07
     Sega
    0.06
    unifu
    0.06
     issu
    0.06
     httpResponse
    0.06
     hava
    0.06
    iams
    0.06
     RuntimeMethod
    0.06
    .onOptionsItemSelected
    0.06
    Act Density 0.012%

    No Known Activations