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

    Neuronpedia

    INDEX
    Explanations

    process steps and stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вшийся
    0.38
     mít
    0.38
     unconsciously
    0.37
     የሆነ
    0.36
     ännu
    0.36
     مدر
    0.36
     fratt
    0.36
    ستی
    0.36
    Https
    0.35
     míst
    0.35
    POSITIVE LOGITS
     of
    0.52
    และการ
    0.48
    owanie
    0.47
    过程中
    0.46
    process
    0.46
    を行い
    0.46
    creation
    0.44
     creation
    0.44
     دادن
    0.43
    of
    0.43
    Act Density 0.039%

    No Known Activations