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

    Neuronpedia

    INDEX
    Explanations

    Art, history, development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    某一
    -0.07
    不可或
    -0.07
    ꙋ
    -0.07
     grosse
    -0.07
     Rao
    -0.07
    -Semit
    -0.07
    𝛽
    -0.07
     offenses
    -0.07
    �
    -0.06
    ij
    -0.06
    POSITIVE LOGITS
     installed
    0.07
    �
    0.07
     |
    0.07
     syslog
    0.07
     overhaul
    0.07
    _metrics
    0.07
    getName
    0.07
    _term
    0.07
     зим
    0.07
    SYSTEM
    0.07
    Act Density 0.202%

    No Known Activations