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

    Neuronpedia

    INDEX
    Explanations

    energy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imus
    -0.07
    occer
    -0.07
     staging
    -0.07
    vis
    -0.06
    BUS
    -0.06
    .Login
    -0.06
    ㉱
    -0.06
    ]^
    -0.06
     الاجتماعي
    -0.06
     cms
    -0.06
    POSITIVE LOGITS
    (dt
    0.07
    界的
    0.07
    嘤
    0.07
     proyectos
    0.06
    希
    0.06
    お互
    0.06
     успешно
    0.06
    gallery
    0.06
    chants
    0.06
    isFunction
    0.06
    Act Density 0.025%

    No Known Activations