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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NN
    -0.07
     scanned
    -0.06
    Delete
    -0.06
    logged
    -0.06
    Na
    -0.06
    mur
    -0.06
     люб
    -0.06
    assin
    -0.06
    분
    -0.06
    ')))↵
    -0.06
    POSITIVE LOGITS
    .copy
    0.07
     nhiêu
    0.06
    =YES
    0.06
    √
    0.06
     Change
    0.06
     (*)
    0.06
    .getWidth
    0.06
     плав
    0.06
    ")==
    0.06
    /Runtime
    0.06
    Act Density 0.022%

    No Known Activations