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

    Neuronpedia

    INDEX
    Explanations

    Modi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decrement
    -0.07
    enance
    -0.06
    Ign
    -0.06
     Klan
    -0.06
     profits
    -0.06
    ales
    -0.06
    romise
    -0.06
     Haskell
    -0.06
    _in
    -0.06
    ling
    -0.06
    POSITIVE LOGITS
     Modi
    0.08
    ителя
    0.07
    .navigationController
    0.07
     Multimedia
    0.07
    jav
    0.07
    prm
    0.07
    ("//
    0.06
    До
    0.06
     dosy
    0.06
     比
    0.06
    Act Density 0.003%

    No Known Activations