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

    Neuronpedia

    INDEX
    Explanations

    included

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (firstName
    -0.07
    ọng
    -0.07
    ;(
    -0.07
    Lic
    -0.06
     reflective
    -0.06
    ki
    -0.06
    אפ
    -0.06
    Nos
    -0.06
     Macros
    -0.06
    ublic
    -0.06
    POSITIVE LOGITS
     revolver
    0.07
    Ear
    0.07
     continuation
    0.07
     дал
    0.07
     donn
    0.06
    试图
    0.06
    resco
    0.06
    isdigit
    0.06
    :NSLayout
    0.06
    etary
    0.06
    Act Density 0.063%

    No Known Activations