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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffa
    -0.07
    -gap
    -0.07
     scape
    -0.07
     nonce
    -0.07
     xem
    -0.06
    dız
    -0.06
    Endpoints
    -0.06
    applicant
    -0.06
    iyesi
    -0.06
    “Our
    -0.06
    POSITIVE LOGITS
     Indicates
    0.07
    .communic
    0.06
    ज
    0.06
     церков
    0.06
     roční
    0.06
    ::↵
    0.06
     bis
    0.06
     linestyle
    0.06
     Julian
    0.06
     Stunning
    0.06
    Act Density 0.014%

    No Known Activations