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

    Neuronpedia

    INDEX
    Explanations

    Equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хват
    -0.08
     meet
    -0.07
     волос
    -0.07
     sling
    -0.07
     pictured
    -0.07
     нерв
    -0.07
     meets
    -0.07
     put
    -0.07
    到底
    -0.07
    -ish
    -0.07
    POSITIVE LOGITS
     själva
    0.09
    urnar
    0.08
    dddd
    0.08
     Público
    0.08
     vitamina
    0.08
    ILA
    0.08
     дополнительные
    0.08
    ahayag
    0.08
     Betrag
    0.07
    istan
    0.07
    Act Density 0.006%

    No Known Activations