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

    Neuronpedia

    INDEX
    Explanations

    email addresses and names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tub
    -0.07
     blood
    -0.07
     нельзя
    -0.07
     obvious
    -0.07
    sock
    -0.07
    הבנה
    -0.07
    earth
    -0.07
     máu
    -0.07
    ************************
    -0.06
     slave
    -0.06
    POSITIVE LOGITS
    _('
    0.07
    一瓶
    0.07
    !--
    0.07
    .department
    0.07
     ((!
    0.07
    衝
    0.07
    Seattle
    0.06
    …↵
    0.06
     ‫
    0.06
    旗
    0.06
    Act Density 0.467%

    No Known Activations