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

    Neuronpedia

    INDEX
    Explanations

    Java annotations and access modifiers

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

    program structure or user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oprot
    -0.46
    .
    -0.45
    Response
    -0.42
     return
    -0.41
     rest
    -0.41
    <eos>
    -0.41
     behind
    -0.40
    ia
    -0.40
     for
    -0.40
    ↵↵
    -0.38
    POSITIVE LOGITS
     kasarigan
    1.03
     queſta
    0.75
    ftagPool
    0.65
    quelize
    0.64
     ſich
    0.63
     $_(
    0.62
    niſſe
    0.61
     Administrativna
    0.60
     transfieras
    0.60
     dezelve
    0.60
    Act Density 0.004%

    No Known Activations