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

    Neuronpedia

    INDEX
    Explanations

    Planning and development projects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Supplier
    -0.07
     Hulk
    -0.07
     Defence
    -0.07
    込み
    -0.06
     le
    -0.06
     D
    -0.06
     di
    -0.06
    enko
    -0.06
    込
    -0.06
     Abs
    -0.06
    POSITIVE LOGITS
     conveniently
    0.07
    真的
    0.06
    }','
    0.06
    781
    0.06
     externally
    0.06
    ]),
    0.06
    arem
    0.06
     RAT
    0.06
    (regex
    0.06
    nP
    0.06
    Act Density 0.041%

    No Known Activations