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

    Neuronpedia

    INDEX
    Explanations

    Bayesian statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    altet
    -0.07
     nltk
    -0.07
     eos
    -0.06
    orů
    -0.06
    _SESSION
    -0.06
     cate
    -0.06
    ового
    -0.06
     o
    -0.06
    eno
    -0.06
    	send
    -0.06
    POSITIVE LOGITS
     slapped
    0.06
     crashing
    0.06
     Сам
    0.06
    Slash
    0.06
    .Then
    0.06
    "People
    0.06
     Korea
    0.06
     arranged
    0.06
    →
    0.06
    ()){
    0.06
    Act Density 0.009%

    No Known Activations