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

    Neuronpedia

    INDEX
    Explanations

    specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    That
    0.98
    ;
    0.92
    也
    0.84
    For
    0.84
    Had
    0.83
    Through
    0.83
     through
    0.83
    With
    0.83
    Because
    0.82
    ா
    0.82
    POSITIVE LOGITS
     pediatric
    1.71
     WWE
    1.66
     esports
    1.62
     Bitcoin
    1.60
     aquaculture
    1.59
     Ethereum
    1.58
     Pokémon
    1.56
     cybersecurity
    1.55
     orthodontic
    1.55
     Fortnite
    1.54
    Act Density 1.175%

    No Known Activations