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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agher
    -0.07
     dataframe
    -0.07
    .TextEdit
    -0.06
     Integrity
    -0.06
     harness
    -0.06
     standardized
    -0.06
     bure
    -0.06
    онд
    -0.06
    Wonder
    -0.06
    college
    -0.06
    POSITIVE LOGITS
    فل
    0.06
    wy
    0.06
    614
    0.06
     револю
    0.06
    レン
    0.06
     Vương
    0.06
     χρησιμοποι
    0.06
    tesy
    0.06
    .background
    0.06
    Neill
    0.06
    Act Density 0.047%

    No Known Activations