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

    Neuronpedia

    INDEX
    Explanations

    always

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
     weighted
    -0.06
     strongly
    -0.06
     balancing
    -0.06
     хотя
    -0.06
     relatively
    -0.06
    -player
    -0.06
    =res
    -0.06
    (APP
    -0.06
    ذكر
    -0.06
    POSITIVE LOGITS
     invoices
    0.07
    ElapsedTime
    0.06
    Pin
    0.06
     enslaved
    0.06
    _eth
    0.06
     Pb
    0.06
     celestial
    0.06
    essay
    0.06
    ılır
    0.06
     آم
    0.06
    Act Density 0.013%

    No Known Activations