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

    Neuronpedia

    INDEX
    Explanations

    ISO

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Go
    -0.07
    264
    -0.07
     northwest
    -0.06
    ùy
    -0.06
    _extended
    -0.06
     expans
    -0.06
    731
    -0.06
    gments
    -0.06
    .curr
    -0.06
    /xml
    -0.06
    POSITIVE LOGITS
    を開
    0.06
     vak
    0.06
    HBoxLayout
    0.06
     Αγ
    0.06
     sæ
    0.06
     bibliography
    0.06
     ard
    0.06
    :length
    0.06
    aigned
    0.06
     README
    0.06
    Act Density 0.004%

    No Known Activations