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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     callers
    -0.07
    292
    -0.07
     database
    -0.07
    212
    -0.07
    849
    -0.06
     brands
    -0.06
     apps
    -0.06
    Sw
    -0.06
     kindly
    -0.06
     Alf
    -0.06
    POSITIVE LOGITS
     Instantiate
    0.07
    aul
    0.07
     natuur
    0.06
     ความ
    0.06
     |_
    0.06
    èo
    0.06
    ..."↵
    0.06
    军
    0.06
    iosa
    0.06
     Braun
    0.06
    Act Density 0.005%

    No Known Activations