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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    并不
    -0.07
     свого
    -0.07
     자동차
    -0.07
    ienie
    -0.07
     alumnos
    -0.07
    meleri
    -0.07
     orig
    -0.06
    ść
    -0.06
    etu
    -0.06
     lugares
    -0.06
    POSITIVE LOGITS
    Coming
    0.07
    Give
    0.07
     Hero
    0.06
    โซ
    0.06
    rug
    0.06
     Banner
    0.06
    azing
    0.06
    (AT
    0.06
     audiences
    0.06
     Coming
    0.06
    Act Density 0.011%

    No Known Activations