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

    Neuronpedia

    INDEX
    Explanations

    betray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grid
    -0.07
     схем
    -0.06
    .CenterScreen
    -0.06
    霊
    -0.06
     Cumhuriyeti
    -0.06
    irket
    -0.06
    larındaki
    -0.06
    complexType
    -0.06
     kullanıl
    -0.06
     раньше
    -0.06
    POSITIVE LOGITS
     betrayed
    0.10
     betray
    0.09
     Taiwanese
    0.07
     violate
    0.07
     achieve
    0.07
    租
    0.06
     blob
    0.06
    .tagName
    0.06
     rib
    0.06
    SUR
    0.06
    Act Density 0.004%

    No Known Activations