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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uv
    -0.07
     father
    -0.07
     three
    -0.07
    -device
    -0.07
     faint
    -0.07
    const
    -0.07
     mặt
    -0.07
    .mount
    -0.07
     voice
    -0.06
    št
    -0.06
    POSITIVE LOGITS
    ея
    0.06
    uckland
    0.06
     IOC
    0.06
    ICC
    0.06
     amacı
    0.06
    XT
    0.06
    988
    0.06
     campaigners
    0.06
     따른
    0.06
    ดาห
    0.05
    Act Density 0.078%

    No Known Activations