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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仅次
    -0.07
    쥘
    -0.07
    iostream
    -0.07
     click
    -0.07
     jPanel
    -0.07
    .write
    -0.06
    qus
    -0.06
    panic
    -0.06
    等功能
    -0.06
    促
    -0.06
    POSITIVE LOGITS
    mvc
    0.07
    MB
    0.07
    0.07
     SMA
    0.07
     refurb
    0.07
    wei
    0.07
    .sale
    0.07
     Steele
    0.07
    安い
    0.06
    0.06
    Act Density 0.000%

    No Known Activations