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

    Neuronpedia

    INDEX
    Explanations

    UI actions/elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drank
    -0.08
     analyser
    -0.08
    594
    -0.08
     rainfall
    -0.07
    ORIA
    -0.07
    500
    -0.07
    IVAL
    -0.07
     buffering
    -0.07
     analizar
    -0.07
     sustained
    -0.07
    POSITIVE LOGITS
    _delete
    0.12
     delete
    0.12
    Delete
    0.12
    delete
    0.11
    /delete
    0.11
    .delete
    0.11
     删除
    0.11
    삭제
    0.11
    DELETE
    0.11
     삭제
    0.11
    Act Density 0.012%

    No Known Activations