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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malware
    -0.07
    speaker
    -0.07
    avor
    -0.06
    Keith
    -0.06
     hemos
    -0.06
    们
    -0.06
     Brake
    -0.06
    ЕР
    -0.06
     SMTP
    -0.06
    VID
    -0.06
    POSITIVE LOGITS
    .*;
↵
    0.08
    .Clone
    0.06
     бур
    0.06
    різ
    0.06
    .zh
    0.06
    .pair
    0.06
    prepend
    0.06
     친구
    0.06
    .Comp
    0.06
     Açık
    0.06
    Act Density 0.002%

    No Known Activations