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

    Neuronpedia

    INDEX
    Explanations

    script disabled on error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sas
    0.43
     pouring
    0.41
     Materials
    0.40
    MATERIALS
    0.38
     bahan
    0.38
     Corbin
    0.38
    िसा
    0.38
     Sasha
    0.37
     sausages
    0.37
    Zespół
    0.37
    POSITIVE LOGITS
    Gaming
    0.65
     gambling
    0.64
     gaming
    0.64
     gambler
    0.59
     gamb
    0.56
     Gaming
    0.56
     gamblers
    0.56
    Gamb
    0.55
    gaming
    0.54
     Gambling
    0.54
    Act Density 0.001%

    No Known Activations