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

    Neuronpedia

    INDEX
    Explanations

    references to the subject "it."

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

    "it", "there", or subject followed by "seem" or "appear"

    np_acts-logits-general · gemini-2.0-flash

    how things seem or appear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presumably
    -0.62
    Personendaten
    -0.59
     Presumably
    -0.56
     Likely
    -0.52
    ğından
    -0.50
    cluye
    -0.50
    Aktualisiert
    -0.49
     allegedly
    -0.48
    ViewImports
    -0.48
    likely
    -0.48
    POSITIVE LOGITS
     seem
    1.16
     seems
    1.11
     seemed
    0.93
    seems
    0.90
     Seems
    0.90
    seem
    0.82
     sounds
    0.81
     sound
    0.81
     seam
    0.80
    Seems
    0.80
    Act Density 0.248%

    No Known Activations