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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sense
    -0.07
    Appearance
    -0.06
    Sys
    -0.06
    Hard
    -0.06
    .Icon
    -0.06
     Chew
    -0.06
    Ross
    -0.06
     Fuse
    -0.06
    obi
    -0.06
    	title
    -0.06
    POSITIVE LOGITS
     MEP
    0.07
     ").
    0.07
     tấn
    0.06
    /{
    0.06
     weaknesses
    0.06
    ']).
    0.06
     premises
    0.06
    WER
    0.06
     Sweden
    0.06
     telemetry
    0.06
    Act Density 0.109%

    No Known Activations