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

    Neuronpedia

    INDEX
    Explanations

    write a short story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pasted
    0.96
     incubated
    0.85
    欣赏
    0.85
    ostęp
    0.83
     fournis
    0.82
     boilerplate
    0.81
     parceria
    0.80
    原文
    0.79
     incubating
    0.79
     exemplary
    0.78
    POSITIVE LOGITS
     uw
    0.74
     مو
    0.72
     ENG
    0.68
    TV
    0.67
    ahre
    0.66
    dl
    0.65
    धक
    0.64
    രിച്ചു
    0.64
    ch
    0.64
     choker
    0.64
    Act Density 0.019%

    No Known Activations