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

    Neuronpedia

    INDEX
    Explanations

    fake and pretend scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ITÉ
    0.36
     STYLE
    0.34
     гото
    0.33
     Directly
    0.33
     Ş
    0.33
    ཿ
    0.33
    ただ
    0.32
     underrated
    0.32
     directly
    0.32
     TAM
    0.32
    POSITIVE LOGITS
     fake
    0.94
    假的
    0.90
    假
    0.87
     Fake
    0.82
     faux
    0.81
    Fake
    0.80
     pretend
    0.79
     pretends
    0.79
    fake
    0.77
     pretending
    0.77
    Act Density 0.055%

    No Known Activations