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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wondering
    -0.06
    ляем
    -0.06
    }>
    -0.06
    看见
    -0.06
    Dog
    -0.06
    truck
    -0.06
    watch
    -0.06
    关系
    -0.06
    
    -0.06
    LOGIN
    -0.06
    POSITIVE LOGITS
     روسی
    0.07
    semb
    0.07
     Apostle
    0.07
    .packet
    0.06
    (Max
    0.06
     Approved
    0.06
    _BOOL
    0.06
    IVATE
    0.06
    exemple
    0.06
     광고
    0.06
    Act Density 0.006%

    No Known Activations