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

    Neuronpedia

    INDEX
    Explanations

    formal mathematical notation and logical structures in proofs

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

    proof or argument construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.62
     الرياضيه
    -0.61
    RegistryLite
    -0.57
    setopt
    -0.56
    +#+
    -0.56
     Normdatei
    -0.54
    majánló
    -0.54
    Datuak
    -0.52
    Tikang
    -0.51
     PeEnEo
    -0.51
    POSITIVE LOGITS
     proof
    0.50
    证明
    0.39
     prove
    0.39
     proving
    0.39
     Proof
    0.38
    Proof
    0.38
     proves
    0.36
    證
    0.36
     argument
    0.36
     dimost
    0.36
    Act Density 0.385%

    No Known Activations