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

    Neuronpedia

    INDEX
    Explanations

    Release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     서울
    -0.07
     Angola
    -0.06
    �
    -0.06
     ded
    -0.06
    880
    -0.06
    .tx
    -0.06
     Aer
    -0.06
    �
    -0.06
    _P
    -0.06
     Soap
    -0.06
    POSITIVE LOGITS
     Leslie
    0.08
    labs
    0.07
    ура
    0.07
     disclosures
    0.07
    release
    0.07
    Release
    0.06
     cinnamon
    0.06
    び
    0.06
    없는
    0.06
    [arr
    0.06
    Act Density 0.004%

    No Known Activations