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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     livelihood
    -0.08
     '').
    -0.08
     vezi
    -0.07
     thrive
    -0.07
     tradi
    -0.07
     forging
    -0.07
     pras
    -0.07
    Redo
    -0.07
    eringen
    -0.07
    asab
    -0.07
    POSITIVE LOGITS
     அறிவ
    0.08
     lec
    0.08
     மூ
    0.07
    осто
    0.07
    .multi
    0.07
    .load
    0.07
     Psycho
    0.07
     Kapitel
    0.07
    [...,
    0.07
    /input
    0.07
    Act Density 0.005%

    No Known Activations