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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    حل
    -0.07
     artık
    -0.07
     deposited
    -0.06
    Character
    -0.06
    宋体
    -0.06
     Dev
    -0.06
    ixa
    -0.06
     Cristiano
    -0.06
    ambique
    -0.06
    .rl
    -0.06
    POSITIVE LOGITS
    aleb
    0.07
    確
    0.06
    희
    0.06
    akah
    0.06
     sessionFactory
    0.06
    ΗΜ
    0.06
    ấm
    0.06
     exclus
    0.06
     vyz
    0.06
     lifes
    0.06
    Act Density 0.025%

    No Known Activations