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

    Neuronpedia

    INDEX
    Explanations

    molecules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Language
    -0.06
     усл
    -0.06
     Purdue
    -0.06
    _attr
    -0.06
    932
    -0.06
     Abrams
    -0.06
    acists
    -0.06
     SqlDataReader
    -0.06
    eat
    -0.06
    ！」
    -0.06
    POSITIVE LOGITS
    _Z
    0.07
    -Bar
    0.07
    urent
    0.07
    ......
    0.06
    _quality
    0.06
     lidi
    0.06
    /_
    0.06
    Bin
    0.06
    星
    0.06
    minimal
    0.06
    Act Density 0.043%

    No Known Activations