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

    Neuronpedia

    INDEX
    Explanations

    emap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’é
    -0.08
     simult
    -0.08
    死了
    -0.07
     sommes
    -0.07
     ço
    -0.07
     것도
    -0.07
    甘肃
    -0.07
    Bell
    -0.07
     exercício
    -0.07
    izon
    -0.07
    POSITIVE LOGITS
    gba
    0.08
    Behaviour
    0.07
     Examination
    0.07
    sha
    0.07
    dna
    0.07
    广阔的
    0.07
    develop
    0.07
     Sasha
    0.07
    teachers
    0.07
    RAW
    0.07
    Act Density 0.004%

    No Known Activations