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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immobil
    -0.09
     nebul
    -0.08
     الع
    -0.08
    elő
    -0.08
     Immobil
    -0.08
     avant
    -0.08
     nationalist
    -0.07
     embark
    -0.07
     debut
    -0.07
     notably
    -0.07
    POSITIVE LOGITS
     mirrored
    0.10
     symmetry
    0.10
    rored
    0.10
    mirror
    0.09
    partner
    0.09
    Partner
    0.08
     symmetrical
    0.08
     Partner
    0.08
    Responses
    0.08
    sym
    0.08
    Act Density 0.032%

    No Known Activations