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

    Neuronpedia

    INDEX
    Explanations

    grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ätt
    -0.06
    abolic
    -0.06
     cooled
    -0.06
    adığ
    -0.06
     çev
    -0.06
    icter
    -0.06
    ories
    -0.06
    rar
    -0.06
    ceptions
    -0.06
     Ve
    -0.06
    POSITIVE LOGITS
     Choosing
    0.07
    用户
    0.06
     duplicated
    0.06
    (frames
    0.06
     تلفن
    0.06
    darwin
    0.06
    decision
    0.06
     thankfully
    0.06
     Sonuç
    0.06
     Cem
    0.06
    Act Density 0.028%

    No Known Activations