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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and control flow structures

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

    function arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.52
    twimg
    -0.47
    VersionUID
    -0.47
    /**
    -0.46
    Datuak
    -0.45
     pleaſure
    -0.45
    MessageOf
    -0.43
    +#+
    -0.42
     pinulongan
    -0.42
     compteur
    -0.41
    POSITIVE LOGITS
    DebuggerNonUser
    0.43
    DoubleQuotes
    0.42
    aman
    0.39
     demand
    0.39
     front
    0.38
     fine
    0.37
    front
    0.37
    ResumeLayout
    0.37
    TRAILING
    0.36
     static
    0.36
    Act Density 0.018%

    No Known Activations