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

    Neuronpedia

    INDEX
    Explanations

    worth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Henrik
    -0.08
     му
    -0.07
     реб
    -0.06
    �
    -0.06
     jamais
    -0.06
     pravděpodob
    -0.06
     μά
    -0.06
    oren
    -0.06
    contador
    -0.06
     боку
    -0.06
    POSITIVE LOGITS
     Seç
    0.06
     (?)
    0.06
    (sim
    0.06
    LG
    0.06
    .Est
    0.06
     STOCK
    0.06
    cut
    0.06
     amounted
    0.06
    ATALOG
    0.06
     Worth
    0.06
    Act Density 0.002%

    No Known Activations