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

    web file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.95
    AndEndTag
    -0.85
     myſelf
    -0.82
    AnchorStyles
    -0.81
    IntoConstraints
    -0.79
    <unused1>
    -0.75
    <unused41>
    -0.75
    <unused28>
    -0.74
    <unused16>
    -0.74
    <unused3>
    -0.74
    POSITIVE LOGITS
     .
    0.37
    +".
    0.35
    }.
    0.35
    +'.
    0.35
    ．
    0.33
    。
    0.32
    $.
    0.32
    _.
    0.32
    .
    0.32
    }$.
    0.31
    Act Density 0.018%

    No Known Activations