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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gr
    -0.07
     Пет
    -0.07
     sınır
    -0.07
     γλώ
    -0.07
     Steering
    -0.07
     Sco
    -0.06
    benh
    -0.06
     grants
    -0.06
     Handbook
    -0.06
     
    -0.06
    POSITIVE LOGITS
    (/\
    0.07
     searchTerm
    0.06
     bulunan
    0.06
    eless
    0.06
    .fromCharCode
    0.06
     ryb
    0.06
    _used
    0.06
    .grp
    0.06
     leaderboard
    0.06
    :[],↵
    0.06
    Act Density 0.000%

    No Known Activations