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

    Neuronpedia

    INDEX
    Explanations

    Comparison operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fec
    -0.07
    -toast
    -0.07
     derived
    -0.07
    .manage
    -0.07
     سفر
    -0.06
    _journal
    -0.06
    919
    -0.06
     Naughty
    -0.06
    infer
    -0.06
    PELL
    -0.06
    POSITIVE LOGITS
    (option
    0.07
    Figure
    0.07
     어떻게
    0.06
    SPI
    0.06
     =================================
    0.06
    Об
    0.06
     Nicholas
    0.06
    cut
    0.06
    iden
    0.06
    >);↵
    0.06
    Act Density 0.008%

    No Known Activations