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

    Neuronpedia

    INDEX
    Explanations

    ellipses or pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    full review or profile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.64
     Majefty
    -0.63
     enfans
    -0.62
     Monfieur
    -0.59
    TagMode
    -0.58
    arangay
    -0.57
     feroit
    -0.57
    hematical
    -0.57
    μβρίου
    -0.56
     ſche
    -0.55
    POSITIVE LOGITS
    ...
    1.09
     ...
    0.94
     [...
    0.77
    ...,
    0.75
    …
    0.75
    (...)
    0.74
     (...)
    0.74
    ....
    0.73
     (...
    0.72
    ,...
    0.71
    Act Density 0.026%

    No Known Activations