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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hammer
    -0.07
    玥
    -0.07
    磹
    -0.07
    смотреть
    -0.07
     мастер
    -0.07
    ختص
    -0.07
     ambassador
    -0.06
    *angstrom
    -0.06
     وم
    -0.06
     ?>;↵
    -0.06
    POSITIVE LOGITS
    usu
    0.08
     diversion
    0.07
    OX
    0.07
     GRAPH
    0.07
     CSL
    0.07
     Analysis
    0.07
    上次
    0.07
    \modules
    0.07
    숭
    0.07
     الدني
    0.07
    Act Density 0.030%

    No Known Activations