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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TRS
    -0.07
    תחוש
    -0.07
    教堂
    -0.06
    .equalsIgnoreCase
    -0.06
     manufactured
    -0.06
     finest
    -0.06
     feder
    -0.06
    .itemId
    -0.06
    (username
    -0.06
    Eine
    -0.06
    POSITIVE LOGITS
     &$
    0.07
    bec
    0.06
    '})↵↵
    0.06
     Kraft
    0.06
     Hook
    0.06
    辩论
    0.06
    bé
    0.06
    🧐
    0.06
    分开
    0.06
    arte
    0.06
    Act Density 0.032%

    No Known Activations