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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    et
    -0.08
    ets
    -0.07
     which
    -0.07
     anew
    -0.07
     đặt
    -0.07
    ecessarily
    -0.07
    ET
    -0.07
    .UnitTesting
    -0.07
     beasts
    -0.06
    ately
    -0.06
    POSITIVE LOGITS
     MÜ
    0.08
     кож
    0.07
    tsky
    0.07
    dialogs
    0.07
    सम
    0.07
    Proposal
    0.07
    รณ
    0.06
    SR
    0.06
    чик
    0.06
     Волод
    0.06
    Act Density 0.166%

    No Known Activations