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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iri
    -0.07
    iphy
    -0.06
     frustrated
    -0.06
     pedig
    -0.06
    `()
    -0.06
    \Traits
    -0.06
     رف
    -0.06
    _COMMON
    -0.06
    ocide
    -0.06
     yapı
    -0.06
    POSITIVE LOGITS
    ／↵
    0.08
    WINDOWS
    0.07
    แบบ
    0.07
     แบบ
    0.07
    881
    0.07
    нес
    0.07
    ُوا
    0.07
    복
    0.07
     \<^
    0.07
    697
    0.07
    Act Density 0.000%

    No Known Activations