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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in HTML or template code

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

    code conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.83
    __":
    -0.81
     PeEnEo
    -0.80
    __':
    -0.74
     geweſen
    -0.74
    <unused20>
    -0.73
    <unused21>
    -0.73
    <unused40>
    -0.73
    <unused17>
    -0.73
    <unused16>
    -0.73
    POSITIVE LOGITS
     locu
    0.31
     favour
    0.31
     viss
    0.28
     proper
    0.27
     dobu
    0.26
     django
    0.26
     seg
    0.25
     favourable
    0.25
     mer
    0.25
     favoured
    0.25
    Act Density 0.014%

    No Known Activations