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

    Neuronpedia

    INDEX
    Explanations

    code structure labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    废
    0.41
     रेट
    0.39
    果
    0.38
     解析
    0.38
    Otros
    0.38
    För
    0.37
    டித்து
    0.37
    OSH
    0.37
    ärte
    0.37
     Stabilization
    0.37
    POSITIVE LOGITS
    :
    0.44
    '
    0.42
     and
    0.41
    tains
    0.39
    ):
    0.39
     inmobili
    0.38
     financ
    0.37
     bahwa
    0.37
    ورو
    0.37
     holde
    0.37
    Act Density 0.029%

    No Known Activations