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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pip
    -0.08
    "P
    -0.08
    rapid
    -0.07
    p
    -0.07
    apol
    -0.07
     Pon
    -0.07
     depression
    -0.07
     Pom
    -0.07
     fp
    -0.07
     pon
    -0.07
    POSITIVE LOGITS
     ازدواج
    0.08
    Lista
    0.08
     Entity
    0.07
    建設
    0.07
    (at
    0.07
    _dat
    0.07
    HEET
    0.06
    etheless
    0.06
     investing
    0.06
     عشق
    0.06
    Act Density 0.227%

    No Known Activations