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

    Neuronpedia

    INDEX
    Explanations

    characters used in string manipulations and operations

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

    C++ or C# code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -1.02
    Autoritní
    -0.96
    Hochspringen
    -0.92
    AndEndTag
    -0.90
    CodedInputStream
    -0.89
     betweenstory
    -0.84
    ParallelGroup
    -0.83
    )");
    -0.82
    ')")
    -0.79
     ")");
    -0.78
    POSITIVE LOGITS
    WriteLiteral
    0.64
    ☝
    0.53
    "\
    0.51
     .=
    0.51
     Sto
    0.50
    Bout
    0.49
     Bout
    0.48
     "\
    0.47
    fits
    0.47
     rodin
    0.46
    Act Density 0.032%

    No Known Activations