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

    Neuronpedia

    INDEX
    Explanations

    mathematical and programming expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CGSize
    0.53
    >∗</
    0.52
     السادس
    0.50
    多年的
    0.49
    EOF
    0.48
    失望
    0.48
    膂
    0.48
    Ⅹ
    0.48
     esfor
    0.47
    下来的
    0.47
    POSITIVE LOGITS
     ছাত্রলীগ
    0.56
    teen
    0.52
    max
    0.52
    mead
    0.50
    0.49
    hiyan
    0.49
    graphs
    0.49
    jy
    0.49
    ane
    0.49
     symbolically
    0.48
    Act Density 0.206%

    No Known Activations