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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    twimg
    -0.54
    parab
    -0.50
     driver
    -0.50
    preter
    -0.47
    ‏‏
    -0.47
    Instantiation
    -0.47
    gink
    -0.47
    swire
    -0.46
    ropoda
    -0.46
    鰭
    -0.45
    POSITIVE LOGITS
    FormState
    0.56
    iked
    0.55
     OFDb
    0.53
     FetchType
    0.52
    setVerticalGroup
    0.52
    hdessä
    0.50
    valdo
    0.49
    __":
    0.49
    lenia
    0.48
    unknownFields
    0.47
    Act Density 0.002%

    No Known Activations