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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    述
    -0.06
     summarized
    -0.06
     CAM
    -0.06
     cemetery
    -0.06
    .deep
    -0.06
    amura
    -0.06
     associates
    -0.06
     YT
    -0.06
    %E
    -0.06
    itant
    -0.06
    POSITIVE LOGITS
    sil
    0.07
    ดร
    0.07
     By
    0.07
     편
    0.07
     ar
    0.07
    äß
    0.06
    ?“
    0.06
    ably
    0.06
    ↵↵
    0.06
     Charleston
    0.06
    Act Density 0.001%

    No Known Activations