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

    Neuronpedia

    INDEX
    Explanations

    explicitly stated information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idbody
    0.40
     考え
    0.39
    ยายาม
    0.37
     aprendizaje
    0.36
    discipl
    0.36
     ঘটন
    0.36
     perkembangan
    0.36
     tokamak
    0.36
    ത്തിലേക്ക്
    0.35
     ontwikkeling
    0.34
    POSITIVE LOGITS
     explicitly
    0.88
    明确
    0.77
     explicit
    0.74
    explicit
    0.73
     expressly
    0.71
     Explicit
    0.66
    Explicit
    0.65
     advertised
    0.65
     advertise
    0.63
     upfront
    0.61
    Act Density 0.290%

    No Known Activations