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

    Neuronpedia

    INDEX
    Explanations

    parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Webseite
    -0.07
    Alignment
    -0.07
     cuk
    -0.06
    爱
    -0.06
     نظ
    -0.06
    Authorities
    -0.06
    SW
    -0.06
     **/↵
    -0.06
     gases
    -0.06
    Hierarchy
    -0.06
    POSITIVE LOGITS
    าตร
    0.07
    �
    0.06
     vô
    0.06
     حد
    0.06
     applied
    0.06
    PLEMENT
    0.06
    ····
    0.06
     plagued
    0.06
    ATFORM
    0.06
    inclu
    0.06
    Act Density 0.014%

    No Known Activations