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

    Neuronpedia

    INDEX
    Explanations

    trans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     argue
    -0.08
    てきた
    -0.07
    乃是
    -0.07
     promotes
    -0.07
     boutique
    -0.07
     Turner
    -0.07
     showModal
    -0.07
    —"
    -0.07
     hallmark
    -0.07
     raced
    -0.07
    POSITIVE LOGITS
     yOffset
    0.07
    oko
    0.07
    搅拌
    0.07
    shuffle
    0.07
    .Yes
    0.07
    流动
    0.06
    dıkl
    0.06
    的角度
    0.06
    akt
    0.06
    _Trans
    0.06
    Act Density 0.004%

    No Known Activations