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

    Neuronpedia

    INDEX
    Explanations

    enjoy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     can
    -0.11
     will
    -0.11
    will
    -0.08
     would
    -0.07
     has
    -0.07
     Will
    -0.07
     have
    -0.07
     should
    -0.07
    'll
    -0.06
     recently
    -0.06
    POSITIVE LOGITS
     dès
    0.08
    ��
    0.07
     CHUNK
    0.07
    邦
    0.06
    +=(
    0.06
    交通
    0.06
     sensitivity
    0.06
     YT
    0.06
     Daddy
    0.06
     prostitution
    0.06
    Act Density 0.700%

    No Known Activations