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

    Neuronpedia

    INDEX
    Explanations

    file path references or import statements in code

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

    Relative file paths

    np_acts-logits-general · gemini-2.0-flash

    directory traversal paths (e.g., `../ ../../ `)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ribune
    -0.52
     RVA
    -0.48
     void
    -0.46
     mess
    -0.46
    penup
    -0.44
    百科
    -0.44
    </h1>
    -0.44
     Ause
    -0.44
     enter
    -0.44
     ว่า
    -0.43
    POSITIVE LOGITS
    ſelves
    1.06
    ſelf
    1.05
     myſelf
    1.04
     Jefus
    1.04
     poffible
    1.01
     '../
    0.99
     purpoſe
    0.94
     houſe
    0.93
    ="../
    0.93
     '../../
    0.93
    Act Density 0.020%

    No Known Activations