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

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phys
    -0.07
    blood
    -0.07
     Scot
    -0.06
    _intr
    -0.06
     Soc
    -0.06
     htt
    -0.06
    _INTR
    -0.06
     KY
    -0.06
    /document
    -0.06
    _sv
    -0.06
    POSITIVE LOGITS
     replacement
    0.11
     replace
    0.11
     replaced
    0.11
     replacements
    0.10
     replacing
    0.10
    Replace
    0.10
     replaces
    0.09
     Replace
    0.09
    .replaceAll
    0.08
     Replacement
    0.08
    Act Density 0.022%

    No Known Activations