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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and branching logic in code

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

    Tokens after closing curly brackets

    np_acts-logits-general · gemini-2.0-flash

    code control flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    niksi
    -0.51
    دار
    -0.47
    roj
    -0.46
    urgo
    -0.45
     parfüm
    -0.45
     multa
    -0.45
    Bar
    -0.45
    ALLOW
    -0.44
    RowCount
    -0.44
    baran
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.89
     للمعارف
    0.85
    /*
    0.84
    writeFieldEnd
    0.82
    +#+#
    0.77
    //
    0.76
    ########.
    0.76
    Vidite
    0.76
     समीक्षाओं
    0.76
    sidemargin
    0.76
    Act Density 0.019%

    No Known Activations