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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pursue
    -0.08
     Б
    -0.07
     Feel
    -0.07
     (++
    -0.07
    /"↵↵
    -0.07
    __↵↵
    -0.07
    Př
    -0.07
     Feet
    -0.06
     obscure
    -0.06
    udios
    -0.06
    POSITIVE LOGITS
     atheist
    0.07
     entreprise
    0.06
     Diary
    0.06
    =""></
    0.06
    neck
    0.06
     schizophren
    0.06
     Checking
    0.06
     richest
    0.06
     terribly
    0.06
     unpack
    0.06
    Act Density 0.020%

    No Known Activations