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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and related passive constructions

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

    German auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fjor
    -0.44
    Jenn
    -0.44
    uurs
    -0.44
    ainte
    -0.43
     hű
    -0.43
     Sensitivity
    -0.43
    erialize
    -0.43
    あの
    -0.42
    jshint
    -0.42
    Cif
    -0.41
    POSITIVE LOGITS
     wordt
    1.42
     werd
    1.26
     worden
    1.25
     wird
    1.09
     werden
    1.00
    Wird
    0.96
     Wird
    0.96
    wird
    0.91
     wurde
    0.80
    werden
    0.79
    Act Density 0.001%

    No Known Activations