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

    Neuronpedia

    INDEX
    Explanations

    softens expression or conveys feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    outh
    0.42
     Organizational
    0.41
     Fe
    0.41
     Analysis
    0.41
     evaluation
    0.40
     Eval
    0.39
     George
    0.39
    azz
    0.39
     Images
    0.39
     Fields
    0.39
    POSITIVE LOGITS
     manusia
    0.43
     বর্তমান
    0.41
     irgendwo
    0.41
     কোথাও
    0.40
     পণ
    0.40
    অর্থাৎ
    0.40
    ื่อย
    0.40
     puffed
    0.40
    indungi
    0.39
    ◝
    0.39
    Act Density 0.000%

    No Known Activations