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

    Neuronpedia

    INDEX
    Explanations

    new york

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Garth
    0.30
    Gosudarstvennyj
    0.30
     investi
    0.30
     heterod
    0.29
     potentiel
    0.29
     prerog
    0.29
     fungsi
    0.28
     biotech
    0.28
     adsorb
    0.28
     funkc
    0.28
    POSITIVE LOGITS
    {
    0.35
    to
    0.32
    ;
    0.32
    null
    0.31
    self
    0.30
    text
    0.30
    color
    0.30
    true
    0.29
    full
    0.29
    new
    0.28
    Act Density 0.160%

    No Known Activations