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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chase
    -0.07
    ural
    -0.07
    Flight
    -0.07
    카라
    -0.07
     صند
    -0.07
    esus
    -0.06
     seeks
    -0.06
     proport
    -0.06
    亿元
    -0.06
     prick
    -0.06
    POSITIVE LOGITS
    -msg
    0.06
    _abort
    0.06
     akci
    0.06
    께서
    0.06
    .Node
    0.06
    fft
    0.06
    )e
    0.06
    deen
    0.05
    (line
    0.05
     EEPROM
    0.05
    Act Density 0.053%

    No Known Activations