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

    Neuronpedia

    INDEX
    Explanations

    Hacker News

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     البر
    -0.07
    EMPLATE
    -0.06
    relationships
    -0.06
    _song
    -0.06
     replacement
    -0.06
     negate
    -0.06
    ocate
    -0.06
    /AFP
    -0.06
    thern
    -0.06
     MPs
    -0.06
    POSITIVE LOGITS
     ET
    0.07
    っ
    0.07
    .jdesktop
    0.07
    ()'
    0.06
     consumed
    0.06
    ="{
    0.06
     -=
    0.06
    (intent
    0.06
     Extra
    0.06
    相当
    0.06
    Act Density 0.003%

    No Known Activations