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

    Neuronpedia

    INDEX
    Explanations

    items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solitude
    -0.07
    òa
    -0.07
    ่ว
    -0.07
    苕
    -0.07
    썰
    -0.07
     kiện
    -0.07
     digits
    -0.07
    idia
    -0.06
    arial
    -0.06
     claw
    -0.06
    POSITIVE LOGITS
    第一章
    0.08
     setting
    0.07
    _radio
    0.07
    ary
    0.07
     musica
    0.07
    Rest
    0.06
    	table
    0.06
     actividad
    0.06
    ]");↵
    0.06
    價
    0.06
    Act Density 0.003%

    No Known Activations