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

    Neuronpedia

    INDEX
    Explanations

    words preceding specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Acetoxy
    1.07
    Watercolor
    1.06
     Voici
    1.05
     Defts
    0.98
    Pedido
    0.98
     Elektrokh
    0.98
    Perfil
    0.98
    Acetyl
    0.97
     Jeśli
    0.97
     Développement
    0.95
    POSITIVE LOGITS
     (
    0.76
    [
    0.71
    (
    0.70
    /
    0.66
     [
    0.64
    <
    0.64
     moral
    0.63
    <em>
    0.62
     medical
    0.62
     religious
    0.61
    Act Density 1.096%

    No Known Activations