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

    Neuronpedia

    INDEX
    Explanations

    code and data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EVE
    -0.07
     sogar
    -0.06
     afr
    -0.06
     أي
    -0.06
     champion
    -0.06
    emotion
    -0.06
    純
    -0.06
     Ep
    -0.06
    crate
    -0.06
    (super
    -0.06
    POSITIVE LOGITS
    .addTo
    0.07
     제출
    0.07
    Bring
    0.06
     Cho
    0.06
    methodPointerType
    0.06
    减
    0.06
     SignUp
    0.06
    رق
    0.06
     engages
    0.06
     Bring
    0.06
    Act Density 0.000%

    No Known Activations