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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stalls
    -0.07
    .false
    -0.07
    想要
    -0.07
     fry
    -0.07
    thes
    -0.07
    ्ध
    -0.06
     diligently
    -0.06
    树
    -0.06
    ル
    -0.06
    ()?>
    -0.06
    POSITIVE LOGITS
    .Engine
    0.07
     TypeName
    0.06
    @login
    0.06
     httpClient
    0.06
     olm
    0.06
     コ
    0.06
     Barber
    0.06
    cluster
    0.06
    comm
    0.06
    eneration
    0.06
    Act Density 0.012%

    No Known Activations