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

    Neuronpedia

    INDEX
    Explanations

    extends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Colonial
    -0.07
     کو
    -0.06
    版本
    -0.06
     disclosures
    -0.06
     Village
    -0.06
     Attachment
    -0.06
     sizi
    -0.06
     Tut
    -0.06
    цький
    -0.06
    ,—
    -0.06
    POSITIVE LOGITS
    odega
    0.06
     Summer
    0.06
    riott
    0.06
    irut
    0.06
     Gaussian
    0.06
    (binary
    0.06
     cellular
    0.06
    _bank
    0.06
     delivers
    0.06
    EDURE
    0.06
    Act Density 0.007%

    No Known Activations