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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -vesm
    -0.07
    %%%%
    -0.06
    icopt
    -0.06
    owned
    -0.06
     Mana
    -0.06
    _Normal
    -0.06
    _regex
    -0.06
    bum
    -0.06
    adies
    -0.06
    `,`
    -0.06
    POSITIVE LOGITS
     ราย
    0.07
     HDD
    0.07
     Desde
    0.07
    .ico
    0.07
     zajist
    0.06
    ندر
    0.06
    .Submit
    0.06
     FormBuilder
    0.06
     talep
    0.06
    Rus
    0.06
    Act Density 0.001%

    No Known Activations