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

    Neuronpedia

    INDEX
    Explanations

    ained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⯑
    -0.08
    �
    -0.08
    聚
    -0.08
    .piece
    -0.07
    מוע
    -0.07
    ǔ
    -0.07
    Est
    -0.07
    -figure
    -0.07
    Enter
    -0.07
    uper
    -0.06
    POSITIVE LOGITS
     THROW
    0.07
    𝑴
    0.07
    .toLowerCase
    0.07
    𝑭
    0.07
     CONTR
    0.07
     שנים
    0.07
     deficiency
    0.07
    活跃
    0.07
    佩服
    0.07
     TD
    0.07
    Act Density 0.001%

    No Known Activations