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

    Neuronpedia

    INDEX
    Explanations

    code, file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Insets
    -0.07
     filetype
    -0.07
    (Address
    -0.07
     created
    -0.06
    剣
    -0.06
    ensity
    -0.06
    .setValue
    -0.06
    _Adjust
    -0.06
    _keeper
    -0.06
    (Integer
    -0.06
    POSITIVE LOGITS
     Louisville
    0.06
     모집
    0.06
     needles
    0.06
     dias
    0.06
    empor
    0.06
    checked
    0.06
    vm
    0.06
    843
    0.06
     Zot
    0.05
     extremists
    0.05
    Act Density 0.188%

    No Known Activations