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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     વધારે
    -0.08
     rosemary
    -0.08
     સ
    -0.08
     બંધ
    -0.08
     doll
    -0.08
    ીસ
    -0.08
     આખ
    -0.07
     सरकारले
    -0.07
     થી
    -0.07
     сб
    -0.07
    POSITIVE LOGITS
    719
    0.08
    烟
    0.08
     prover
    0.07
    San
    0.07
    san
    0.07
    -message
    0.07
    prog
    0.07
     Smoke
    0.07
    গুল
    0.07
    াঙ্গ
    0.07
    Act Density 0.000%

    No Known Activations