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

    Neuronpedia

    INDEX
    Explanations

    elements of personal narrative and reflections about daily life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    completion or ending (finally, finishing, finished)

    np_acts-logits-general · gemini-2.0-flash

    past actions and completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    当时的
    -0.59
    例えば
    -0.59
     Kommune
    -0.58
     suffit
    -0.58
    たとえば
    -0.58
    MMV
    -0.57
     riêng
    -0.56
    hver
    -0.56
    /=
    -0.56
    彼らは
    -0.56
    POSITIVE LOGITS
     finally
    0.93
     finishing
    0.92
     FINALLY
    0.91
    finally
    0.90
    Busy
    0.82
     update
    0.82
     endlich
    0.82
    finishing
    0.81
     sibuk
    0.80
     Finishing
    0.78
    Act Density 0.467%

    No Known Activations