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

    Neuronpedia

    INDEX
    Explanations

    blog post tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ETweet
    -0.08
    dog
    -0.07
    alphabet
    -0.07
     triples
    -0.06
     thirsty
    -0.06
    yy
    -0.06
    .players
    -0.06
    Name
    -0.06
     clocks
    -0.06
     doktor
    -0.06
    POSITIVE LOGITS
    isson
    0.08
    discover
    0.07
     Nebraska
    0.07
    .VK
    0.06
    _DISCONNECT
    0.06
    \\/
    0.06
    ASON
    0.06
     Educ
    0.06
    IntegerField
    0.06
     ensuring
    0.06
    Act Density 0.000%

    No Known Activations