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

    Neuronpedia

    INDEX
    Explanations

    ov

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erne
    -0.06
     tag
    -0.06
     Wasser
    -0.06
    	ti
    -0.06
    	register
    -0.06
    .blit
    -0.06
    undy
    -0.06
    ]
    -0.06
     ederek
    -0.06
    better
    -0.06
    POSITIVE LOGITS
     Innov
    0.07
     sess
    0.07
    IFT
    0.07
    #ab
    0.07
    novation
    0.06
     nhật
    0.06
     prompted
    0.06
     Passage
    0.06
     Revised
    0.06
     Шев
    0.06
    Act Density 0.000%

    No Known Activations