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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ศ
    -0.07
    เช
    -0.07
     giú
    -0.06
    .aspect
    -0.06
     العالمية
    -0.06
    (Enum
    -0.06
    桹
    -0.06
    还算
    -0.06
    เข
    -0.06
     בשנת
    -0.06
    POSITIVE LOGITS
     progressive
    0.09
    _lbl
    0.08
     Mobil
    0.07
    血脂
    0.07
    势力
    0.07
     modular
    0.07
     мягк
    0.07
    	Error
    0.07
    ility
    0.07
    ("~
    0.07
    Act Density 0.001%

    No Known Activations