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

    Neuronpedia

    INDEX
    Explanations

    say story

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    点击查看
    -0.08
    (BitConverter
    -0.07
    �
    -0.07
    +)\
    -0.07
     살아
    -0.07
    朽
    -0.07
    plete
    -0.07
    ')?></
    -0.06
    一览
    -0.06
    蘩
    -0.06
    POSITIVE LOGITS
    <Project
    0.07
     ordinance
    0.07
    fant
    0.07
    Business
    0.07
    場
    0.07
    Front
    0.07
    蓁
    0.07
    .getIndex
    0.07
    Regression
    0.07
    琰
    0.07
    Act Density 0.001%

    No Known Activations