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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propane
    -0.07
    _EXCEPTION
    -0.06
    버
    -0.06
    _FOR
    -0.06
     essentials
    -0.06
    跡
    -0.06
     配
    -0.06
     Session
    -0.06
    struk
    -0.06
     Essentials
    -0.06
    POSITIVE LOGITS
     folk
    0.07
     indian
    0.07
     receives
    0.07
     bbw
    0.06
     मत
    0.06
    maid
    0.06
     charisma
    0.06
    θηκαν
    0.06
    .bean
    0.06
     Cuban
    0.06
    Act Density 0.046%

    No Known Activations