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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amai
    -0.08
    аму
    -0.07
     dominates
    -0.07
    andez
    -0.07
     addition
    -0.07
    mehr
    -0.07
     Hahn
    -0.07
     dominating
    -0.07
     നവ
    -0.07
     prénom
    -0.07
    POSITIVE LOGITS
     preserve
    0.09
     upang
    0.09
     souvenirs
    0.08
     Preserve
    0.08
     preserving
    0.08
    Collected
    0.08
     Preservation
    0.08
     behoud
    0.08
     sonidos
    0.08
     hati
    0.08
    Act Density 0.014%

    No Known Activations