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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sofa
    -0.06
    _term
    -0.06
     collaborate
    -0.06
    .orange
    -0.06
     dictated
    -0.06
    unately
    -0.06
     deposited
    -0.06
    _normal
    -0.06
     레벨
    -0.06
    .Member
    -0.06
    POSITIVE LOGITS
    converted
    0.07
     Positioned
    0.07
     Προ
    0.07
    listening
    0.06
    	↵	↵
    0.06
    ования
    0.06
     कथ
    0.06
    งใน
    0.06
     góc
    0.06
    replaceAll
    0.06
    Act Density 0.001%

    No Known Activations