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

    Neuronpedia

    INDEX
    Explanations

    epsilon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rush
    -0.06
     sided
    -0.06
    riors
    -0.06
    ished
    -0.06
     onBlur
    -0.06
     NIH
    -0.06
    452
    -0.06
    adors
    -0.06
    �
    -0.06
    Generated
    -0.06
    POSITIVE LOGITS
     capit
    0.07
     Constit
    0.07
     employing
    0.07
     jewellery
    0.06
    /set
    0.06
     utilize
    0.06
     declares
    0.06
    objet
    0.06
    >Create
    0.06
     Mexicans
    0.06
    Act Density 0.008%

    No Known Activations