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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     portions
    -0.07
     Marriage
    -0.07
     murderers
    -0.07
     heirs
    -0.07
     outdoor
    -0.07
     apartments
    -0.07
     mixes
    -0.07
     Methodist
    -0.07
     appeals
    -0.07
     firearms
    -0.07
    POSITIVE LOGITS
    .setAdapter
    0.07
    (_:
    0.07
    $name
    0.07
     система
    0.07
    ened
    0.06
    束缚
    0.06
    Encoded
    0.06
     ***/↵
    0.06
    感受
    0.06
    人体
    0.06
    Act Density 0.004%

    No Known Activations