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

    Neuronpedia

    INDEX
    Explanations

    urls with article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ඉද
    0.90
    града
    0.83
     beatae
    0.79
    <unused454>
    0.77
    <unused2060>
    0.77
     बुध
    0.76
    Transicao
    0.76
    䂺
    0.75
    ្ប
    0.74
    <unused415>
    0.74
    POSITIVE LOGITS
    __
    0.79
     related
    0.77
     sus
    0.73
    wand
    0.72
    ban
    0.72
     жөнүндө
    0.71
    lerine
    0.71
     do
    0.70
    ler
    0.70
     eens
    0.70
    Act Density 0.017%

    No Known Activations