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

    Neuronpedia

    INDEX
    Explanations

    comments and annotations in a programming context

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    -0.41
     I
    -0.36
    ,
    -0.36
    tinya
    -0.35
    After
    -0.35
     
    -0.35
     do
    -0.34
    Do
    -0.33
    Nach
    -0.33
    0
    -0.33
    POSITIVE LOGITS
    msgTypes
    1.02
    majánló
    0.93
    ロウィン
    0.92
     queſta
    0.91
    #+#
    0.90
    iſchen
    0.88
    niſſe
    0.87
    ſicht
    0.87
    rawDesc
    0.85
    [@BOS@]
    0.85
    Act Density 0.055%

    No Known Activations