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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �数
    -0.06
     cars
    -0.06
     Gri
    -0.06
    .Message
    -0.06
    paren
    -0.06
     νό
    -0.06
     respect
    -0.06
     QS
    -0.06
     surre
    -0.06
     Chain
    -0.06
    POSITIVE LOGITS
    *ft
    0.07
    者
    0.07
    (sh
    0.07
    �
    0.06
     Adler
    0.06
     Nobel
    0.06
    *e
    0.06
    (category
    0.06
     enters
    0.06
     questioned
    0.06
    Act Density 0.022%

    No Known Activations