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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ission
    -0.07
    =<
    -0.07
     worldview
    -0.07
     cooler
    -0.07
    تق
    -0.06
    OURS
    -0.06
     виник
    -0.06
     between
    -0.06
    이며
    -0.06
    %,
    -0.06
    POSITIVE LOGITS
     dřev
    0.07
     Innovative
    0.06
     Qed
    0.06
    nocení
    0.06
    posts
    0.06
    入り
    0.06
    .dk
    0.06
     serviços
    0.06
     Afr
    0.06
     저장
    0.06
    Act Density 0.005%

    No Known Activations