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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parametros
    -0.08
    면적
    -0.07
     APIs
    -0.07
    stories
    -0.06
    umps
    -0.06
    ає
    -0.06
    oauth
    -0.06
    fails
    -0.06
    Č
    -0.06
     words
    -0.06
    POSITIVE LOGITS
    -Л
    0.07
     ZZ
    0.06
     reins
    0.06
    )")
    0.06
     bal
    0.06
     opacity
    0.06
    encer
    0.06
    ά
    0.06
     LX
    0.06
     /^[
    0.06
    Act Density 0.012%

    No Known Activations