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

    Neuronpedia

    INDEX
    Explanations

    ATTR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    導
    -0.07
     Marr
    -0.06
    optional
    -0.06
    _up
    -0.06
     scarc
    -0.06
    .cpu
    -0.06
    ump
    -0.06
    vůli
    -0.06
    (Player
    -0.06
    법
    -0.06
    POSITIVE LOGITS
     Epidemi
    0.07
     hemos
    0.07
     zdroj
    0.07
    /alert
    0.06
     stringent
    0.06
    DH
    0.06
    Hello
    0.06
     고
    0.06
     Florence
    0.06
     caract
    0.06
    Act Density 0.007%

    No Known Activations