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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .strings
    -0.07
    .Print
    -0.07
    patch
    -0.06
    (io
    -0.06
     }}↵↵
    -0.06
     ध
    -0.06
     needles
    -0.06
    sys
    -0.06
    YSIS
    -0.06
    FLT
    -0.06
    POSITIVE LOGITS
    toggleClass
    0.06
     goalkeeper
    0.06
     empower
    0.06
     AGAIN
    0.06
     divorced
    0.06
    .HttpServletRequest
    0.06
     Trie
    0.06
    idor
    0.06
     ideologies
    0.06
     Attorney
    0.06
    Act Density 0.068%

    No Known Activations