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

    Neuronpedia

    INDEX
    Explanations

    costs or pricing ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fifty
    0.93
    五十
    0.85
     five
    0.81
    5
    0.79
    0.79
    ٥
    0.77
    fifty
    0.77
    ۵
    0.74
     fifties
    0.74
     पचास
    0.73
    POSITIVE LOGITS
    ப்பையும்
    0.68
    िलायंस
    0.64
    ಿಕೊಂಡ
    0.64
    ంబేద్
    0.63
    WithOptions
    0.63
    arrange
    0.63
    wave
    0.62
     Derivative
    0.62
    பொ
    0.61
    water
    0.60
    Act Density 0.064%

    No Known Activations