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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��取
    -0.07
    _prov
    -0.07
     helfen
    -0.07
    堃
    -0.06
    妲
    -0.06
    燮
    -0.06
    _numeric
    -0.06
     ven
    -0.06
    (lat
    -0.06
     szcz
    -0.06
    POSITIVE LOGITS
    themes
    0.07
     microscope
    0.07
     Ultr
    0.07
    bject
    0.07
     Localization
    0.07
    _strip
    0.06
     Night
    0.06
     stringify
    0.06
    elog
    0.06
    שימה
    0.06
    Act Density 0.072%

    No Known Activations