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

    Neuronpedia

    INDEX
    Explanations

    groups of words commonly used together in sentences, often including prepositions or conjunctions.

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    having
    -0.56
    Having
    -0.56
     contextLoads
    -0.54
     Having
    -0.52
    bewerken
    -0.51
     having
    -0.51
    being
    -0.50
    Transkript
    -0.49
     HAVING
    -0.48
    település
    -0.48
    POSITIVE LOGITS
     several
    0.76
    StoryboardSegue
    0.70
     multiple
    0.66
     plenty
    0.64
     many
    0.61
     some
    0.60
    several
    0.59
     numerous
    0.59
     a
    0.58
     createState
    0.57
    Act Density 4.941%

    No Known Activations