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

    Neuronpedia

    INDEX
    Explanations

    cref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .io
    -0.07
     ně
    -0.07
    ANCE
    -0.07
     July
    -0.07
     فوت
    -0.07
     traff
    -0.06
     metaphor
    -0.06
    _OPER
    -0.06
    aternion
    -0.06
     November
    -0.06
    POSITIVE LOGITS
     cref
    0.10
     आल
    0.06
    .');
↵
    0.06
    ावर
    0.06
    products
    0.06
    alcon
    0.06
    WL
    0.06
     pas
    0.06
    .student
    0.06
    _CR
    0.06
    Act Density 0.000%

    No Known Activations