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

    Neuronpedia

    INDEX
    Explanations

    word definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Temple
    -0.07
    .scala
    -0.07
     ظ
    -0.07
     oppressed
    -0.07
    uga
    -0.06
    唯
    -0.06
    —with
    -0.06
    .Dependency
    -0.06
     chuckled
    -0.06
    cido
    -0.06
    POSITIVE LOGITS
    setFlash
    0.07
     Winter
    0.06
    рак
    0.06
     sns
    0.06
     �
    0.06
     coraz
    0.06
     traces
    0.06
    consts
    0.06
     teaser
    0.06
    (raw
    0.06
    Act Density 0.050%

    No Known Activations