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

    Neuronpedia

    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     venez
    0.42
    ologous
    0.41
     unidirectional
    0.39
     survival
    0.38
     shutdown
    0.38
     shutdowns
    0.37
     heil
    0.36
     hostages
    0.36
    瞬間
    0.35
     voltmeter
    0.35
    POSITIVE LOGITS
    ண்ண
    0.49
    ских
    0.49
     Архи
    0.49
    сез
    0.49
     Existem
    0.48
     Index
    0.47
    СК
    0.46
    మ
    0.46
    ських
    0.46
    יש
    0.46
    Act Density 0.001%

    No Known Activations