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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    хід
    -0.07
    Validity
    -0.07
     dane
    -0.07
     cmb
    -0.06
     #[
    -0.06
     DARK
    -0.06
    _vendor
    -0.06
     edad
    -0.06
     notification
    -0.06
    ừng
    -0.06
    POSITIVE LOGITS
    .')↵
    0.07
    }'↵
    0.06
    "
↵
    0.06
    .")↵
    0.06
    ...")↵
    0.06
     armored
    0.06
    "↵
    0.06
     özgür
    0.06
     Elle
    0.06
     вещества
    0.06
    Act Density 0.029%

    No Known Activations