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

    Neuronpedia

    INDEX
    Explanations

    phrases about locations or spaces

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

    "Place" as a location or position

    np_acts-logits-general · gemini-2.0-flash

    place where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.89
     protoimpl
    -0.86
    OGND
    -0.83
    ViewFeatures
    -0.79
    Datuak
    -0.77
     disponibilités
    -0.75
    "]);
    -0.75
     themſelves
    -0.74
    الإنجليزية
    -0.73
    rungsseite
    -0.72
    POSITIVE LOGITS
     where
    1.05
    Where
    0.86
     places
    0.82
     Where
    0.78
    where
    0.77
     WHERE
    0.75
    places
    0.74
    Places
    0.74
     tempat
    0.70
     place
    0.69
    Act Density 0.093%

    No Known Activations