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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lege
    -0.06
    ühr
    -0.06
    σεων
    -0.06
     cbo
    -0.06
    loading
    -0.05
    ومات
    -0.05
     stray
    -0.05
     contemplated
    -0.05
    quarters
    -0.05
     rigged
    -0.05
    POSITIVE LOGITS
     tăng
    0.07
    引き
    0.07
    _RC
    0.07
     dbg
    0.07
    _LOOK
    0.07
    _CONFIGURATION
    0.07
     초기
    0.07
    CT
    0.07
    /full
    0.06
    SDL
    0.06
    Act Density 0.000%

    No Known Activations