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

    Neuronpedia

    INDEX
    Explanations

    rationing and related actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pokémon
    0.61
     CHLOR
    0.57
    ンの
    0.56
     chlorinated
    0.56
     REST
    0.55
     Pokemon
    0.55
     TEN
    0.54
     NASCAR
    0.54
     KFC
    0.54
     chilli
    0.53
    POSITIVE LOGITS
    p
    0.63
    0.63
    lé
    0.59
    lu
    0.57
    0
    0.57
    ×
    0.56
    x
    0.55
    ll
    0.55
    love
    0.55
    y
    0.55
    Act Density 0.001%

    No Known Activations