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

    Neuronpedia

    INDEX
    Explanations

    paragraphs with high levels of detail and specific context

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

    we also need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tiguan
    -0.44
    EndContext
    -0.44
     adap
    -0.42
    ceğine
    -0.42
    Ɓ
    -0.40
    JEL
    -0.40
    Insee
    -0.39
    PyTuple
    -0.39
    copg
    -0.38
    ⤒
    -0.38
    POSITIVE LOGITS
    SequentialGroup
    0.58
     Bewußt
    0.53
    esistenza
    0.53
     miniaturka
    0.46
     näky
    0.45
    antaranya
    0.43
     femininos
    0.42
     referenties
    0.41
     laikā
    0.41
     Ahnung
    0.41
    Act Density 0.000%

    No Known Activations