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

    Neuronpedia

    INDEX
    Explanations

    presence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plain
    -0.07
     spr
    -0.07
    gold
    -0.06
    	users
    -0.06
     flaws
    -0.06
    .band
    -0.06
    lj
    -0.06
    .Record
    -0.06
    holes
    -0.06
    740
    -0.06
    POSITIVE LOGITS
    ]?
    0.07
    ABCDEFGHI
    0.07
     있고
    0.06
    เทศ
    0.06
    )})
    0.06
     oppression
    0.06
    -init
    0.06
    арат
    0.06
     adult
    0.06
    elerik
    0.06
    Act Density 0.006%

    No Known Activations