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

    Neuronpedia

    INDEX
    Explanations

    neutral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     قم
    -0.06
    .mybatisplus
    -0.06
     объект
    -0.06
    "a
    -0.06
    (origin
    -0.06
     Mathematical
    -0.06
     charging
    -0.06
     getP
    -0.06
    問題
    -0.06
     operate
    -0.06
    POSITIVE LOGITS
    entario
    0.07
    эф
    0.07
     bothering
    0.07
     зовніш
    0.07
     покол
    0.07
    wid
    0.07
    ness
    0.07
     Ger
    0.06
    ewood
    0.06
    ه
    0.06
    Act Density 0.005%

    No Known Activations