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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kavram
    -0.07
    .Member
    -0.06
     ayar
    -0.06
    市场
    -0.06
     scl
    -0.06
     пла
    -0.06
     alo
    -0.06
    ΙΚ
    -0.06
     prostitu
    -0.06
    _"
    -0.06
    POSITIVE LOGITS
    :ｉ
    0.07
     &↵
    0.07
     ###↵
    0.07
    ская
    0.06
    �
    0.06
    (++
    0.06
     Yüksek
    0.06
    /T
    0.06
     EPS
    0.06
    (Form
    0.06
    Act Density 0.006%

    No Known Activations