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

    Neuronpedia

    INDEX
    Explanations

    yet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ackson
    -0.07
    مح
    -0.07
     Roll
    -0.07
    all
    -0.07
    ortion
    -0.06
     reactionary
    -0.06
    anax
    -0.06
     Sand
    -0.06
    formula
    -0.06
     natural
    -0.06
    POSITIVE LOGITS
     yet
    0.08
     아직
    0.08
     chưa
    0.07
    et
    0.07
     نويسنده
    0.07
     zatím
    0.07
    未
    0.07
     未
    0.07
     yacht
    0.07
    (before
    0.06
    Act Density 0.011%

    No Known Activations