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

    Neuronpedia

    INDEX
    Explanations

    development resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parentId
    -0.07
     poop
    -0.06
    けて
    -0.06
     Ch
    -0.06
    そ
    -0.06
     effects
    -0.06
    anca
    -0.06
    อม
    -0.06
     Bears
    -0.06
     underage
    -0.06
    POSITIVE LOGITS
     deser
    0.07
    �n
    0.06
     Companies
    0.06
     κύ
    0.06
     ном
    0.06
    .SELECT
    0.06
     κον
    0.06
     podob
    0.06
     임
    0.06
    rots
    0.06
    Act Density 0.082%

    No Known Activations