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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λικά
    -0.07
    erset
    -0.06
     öngör
    -0.06
     withStyles
    -0.06
    primary
    -0.06
     alors
    -0.06
     entire
    -0.06
    نسان
    -0.06
     spiders
    -0.06
    .Serial
    -0.06
    POSITIVE LOGITS
    ODE
    0.06
     anxious
    0.06
    eptal
    0.06
    	dist
    0.06
     clustering
    0.06
    aq
    0.06
    phthalm
    0.06
     dataset
    0.06
    /u
    0.06
    WG
    0.06
    Act Density 0.000%

    No Known Activations