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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology and relationships

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

    introductory phrases for proofs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     հղումներ
    -0.55
    liothèque
    -0.52
     Chwiliwch
    -0.51
    BufferException
    -0.50
    OOTDTY
    -0.49
     Normdatei
    -0.48
     linkovi
    -0.48
    addPreferred
    -0.47
    UserScript
    -0.47
    HostException
    -0.47
    POSITIVE LOGITS
     first
    0.46
     Савезне
    0.45
     borda
    0.37
    的外
    0.37
     biggest
    0.35
     flap
    0.35
     blessings
    0.34
     schme
    0.33
    しゃれ
    0.33
     Lion
    0.33
    Act Density 0.009%

    No Known Activations