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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dialogue
    -0.07
     Lenovo
    -0.07
    ーチ
    -0.07
    Cheers
    -0.07
     Grinder
    -0.07
    "While
    -0.06
     Michaels
    -0.06
    _smooth
    -0.06
    PLEASE
    -0.06
    alance
    -0.06
    POSITIVE LOGITS
    ++){↵
    0.07
    jug
    0.07
     congressman
    0.07
     inducing
    0.07
     overseeing
    0.06
    ){
↵
    0.06
     conjug
    0.06
    (dx
    0.06
    radio
    0.06
     manage
    0.06
    Act Density 0.001%

    No Known Activations