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

    Neuronpedia

    INDEX
    Explanations

    Quotations/negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еро
    -0.07
    tbl
    -0.07
    chází
    -0.07
    ～
    -0.06
     arrows
    -0.06
    ｢
    -0.06
     typical
    -0.06
     Vz
    -0.06
     verg
    -0.06
    owler
    -0.06
    POSITIVE LOGITS
     그녀
    0.06
     podmín
    0.06
    .compat
    0.06
     blowjob
    0.06
     milf
    0.06
     isNew
    0.06
    postId
    0.06
    فته
    0.06
     Voy
    0.06
    .CLASS
    0.06
    Act Density 0.035%

    No Known Activations