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

    Neuronpedia

    INDEX
    Explanations

    type interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supplements
    -0.08
    (ds
    -0.07
    感染
    -0.07
     Vivo
    -0.07
     respectfully
    -0.07
    (bp
    -0.06
    ﲔ
    -0.06
    istribute
    -0.06
    _SPACE
    -0.06
    枍
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ══
    0.07
     bool
    0.07
    不见了
    0.07
    변
    0.07
    ='',
    0.07
    日常
    0.07
    _frag
    0.07
    �
    0.07
    	ct
    0.07
    Act Density 0.002%

    No Known Activations