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

    Neuronpedia

    INDEX
    Explanations

    Hypothetical situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    James
    -0.06
     Gerald
    -0.06
     departments
    -0.06
     spécial
    -0.06
     Tottenham
    -0.06
     Gregory
    -0.06
     nr
    -0.06
     justification
    -0.06
    Ship
    -0.05
     LIABILITY
    -0.05
    POSITIVE LOGITS
    -х
    0.08
     todo
    0.07
     chaos
    0.07
    _global
    0.06
    .instances
    0.06
     мик
    0.06
    体系
    0.06
    ([],
    0.06
     입니다
    0.06
     resmi
    0.06
    Act Density 0.043%

    No Known Activations