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

    Neuronpedia

    INDEX
    Explanations

    forwarded emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pussy
    -0.08
    fy
    -0.07
     yok
    -0.07
     mastered
    -0.07
    汲
    -0.06
     MLS
    -0.06
    gae
    -0.06
     Gors
    -0.06
     físico
    -0.06
    redo
    -0.06
    POSITIVE LOGITS
    च
    0.08
    ◦
    0.07
    Generally
    0.07
     -----
    0.07
    这样一来
    0.07
    	static
    0.07
     הח
    0.07
     człowiek
    0.07
    Prices
    0.06
     UCHAR
    0.06
    Act Density 0.002%

    No Known Activations