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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

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

    .NET system namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arangay
    -0.90
     queſta
    -0.82
    IntoConstraints
    -0.81
    AsUp
    -0.80
     BoxFit
    -0.80
     GenerationType
    -0.78
     queſto
    -0.77
    ſelf
    -0.76
    alakip
    -0.75
    앫
    -0.75
    POSITIVE LOGITS
    .
    0.32
    <bos>
    0.26
    ↵
    0.24
     "..\..\..\
    0.23
    …
    0.23
    人
    0.23
    q
    0.23
    //}
    0.22
    ti
    0.21
    ile
    0.21
    Act Density 0.000%

    No Known Activations