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

    Neuronpedia

    INDEX
    Explanations

    empirical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /cms
    -0.08
    כתב
    -0.07
    =view
    -0.07
     Eid
    -0.07
     stares
    -0.07
     Yas
    -0.07
    ご覧
    -0.07
    طف
    -0.07
    驾
    -0.07
    .transitions
    -0.07
    POSITIVE LOGITS
     criticism
    0.08
     emulation
    0.07
    지를
    0.06
    荑
    0.06
     evils
    0.06
    村民
    0.06
     empirical
    0.06
    的支持
    0.06
    边缘
    0.06
    并不能
    0.06
    Act Density 0.002%

    No Known Activations