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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iences
    -0.06
     governments
    -0.06
    据
    -0.06
    IAM
    -0.06
    /style
    -0.05
    longitude
    -0.05
    чива
    -0.05
    everyone
    -0.05
    �
    -0.05
    やる
    -0.05
    POSITIVE LOGITS
    TEL
    0.07
    .Ab
    0.07
     tố
    0.07
    .getContext
    0.07
     NCAA
    0.06
     scramble
    0.06
    .Fatal
    0.06
     Activ
    0.06
    &oacute
    0.06
    озя
    0.06
    Act Density 0.030%

    No Known Activations