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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yasal
    -0.06
     pus
    -0.06
    variables
    -0.06
    .iteritems
    -0.06
     Balk
    -0.06
     melhor
    -0.06
     Mol
    -0.06
    .forward
    -0.05
    Dataset
    -0.05
     Lust
    -0.05
    POSITIVE LOGITS
    átku
    0.07
     jednotliv
    0.07
     restoring
    0.07
    sha
    0.06
    ointment
    0.06
    oodoo
    0.06
     getClient
    0.06
    referer
    0.06
    -history
    0.06
    skins
    0.06
    Act Density 0.000%

    No Known Activations