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

    Neuronpedia

    INDEX
    Explanations

    Use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аг
    -0.07
    ційного
    -0.07
    へ
    -0.07
     заверш
    -0.07
    ालत
    -0.06
    алом
    -0.06
    $field
    -0.06
    Monitoring
    -0.06
    adows
    -0.06
    .header
    -0.06
    POSITIVE LOGITS
    ปล
    0.07
    IW
    0.06
    ��
    0.06
    PIP
    0.06
     pleas
    0.06
     summers
    0.06
    ITA
    0.06
    into
    0.06
    -Pack
    0.06
    (shared
    0.06
    Act Density 0.001%

    No Known Activations