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

    Neuronpedia

    INDEX
    Explanations

    nested parentheses and brackets in code snippets

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

    code and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
    ↵
    -0.41
    ↵↵↵
    -0.40
         
    -0.40
     Kem
    -0.40
     Krä
    -0.39
                 
    -0.39
     Blom
    -0.37
        
    -0.37
     Burch
    -0.36
    POSITIVE LOGITS
    __(/*!
    0.82
     '\\;'
    0.75
    帖最后由
    0.75
     JpaRepository
    0.71
     Wiktionnaire
    0.68
    0.68
    IntoConstraints
    0.65
    SharedCtor
    0.65
    SourceChecksum
    0.65
    /*
    0.65
    Act Density 0.087%

    No Known Activations