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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _parameter
    -0.07
    foto
    -0.06
     parents
    -0.06
     NPCs
    -0.06
     amazed
    -0.06
    яс
    -0.06
    story
    -0.06
     generado
    -0.06
     gerekli
    -0.06
     exciting
    -0.06
    POSITIVE LOGITS
    rollable
    0.08
    ίσ
    0.07
    IData
    0.06
    pcodes
    0.06
    xdd
    0.06
     gson
    0.06
     electric
    0.06
     Overnight
    0.06
     programm
    0.06
     друж
    0.06
    Act Density 0.057%

    No Known Activations