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

    Neuronpedia

    INDEX
    Explanations

    and, commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     далеко
    -0.07
    mıştı
    -0.07
    堍
    -0.07
    🎿
    -0.07
    沿
    -0.07
    uspend
    -0.07
     deadline
    -0.07
     Jaune
    -0.07
     puesto
    -0.07
    たい
    -0.07
    POSITIVE LOGITS
     �
    0.07
     الحكوم
    0.07
    ＾＾
    0.07
    ',{
    0.07
    科技创新
    0.07
    _("
    0.07
     {$
    0.06
    /self
    0.06
     mounting
    0.06
     john
    0.06
    Act Density 0.183%

    No Known Activations