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

    Neuronpedia

    INDEX
    Explanations

    the preposition "on" preceded by several words

    oai_token-act-pair · gemini-2.0-flash

    almost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    day
    -0.89
    Day
    -0.84
     day
    -0.84
    DAY
    -0.80
     Woche
    -0.79
     DAY
    -0.77
     Day
    -0.77
     semana
    -0.71
    week
    -0.70
     week
    -0.69
    POSITIVE LOGITS
     almost
    0.99
     nearly
    0.93
    almost
    0.86
     Almost
    0.86
    Almost
    0.85
    nearly
    0.81
     Nearly
    0.77
     hampir
    0.75
     quase
    0.73
    Nearly
    0.71
    Act Density 0.839%

    No Known Activations