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

    Neuronpedia

    INDEX
    Explanations

    details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STATES
    -0.07
     теперь
    -0.07
     anybody
    -0.07
     Somebody
    -0.06
     INCLUDED
    -0.06
    -tip
    -0.06
     đội
    -0.06
    tracted
    -0.06
     Memories
    -0.06
    (and
    -0.06
    POSITIVE LOGITS
     reel
    0.07
     κοι
    0.07
     cunt
    0.06
     healthier
    0.06
    -twitter
    0.06
    504
    0.06
     filtro
    0.06
    PropertyName
    0.06
     steel
    0.06
    ea
    0.06
    Act Density 0.000%

    No Known Activations