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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pattern
    -0.07
    кас
    -0.07
    errors
    -0.07
    (status
    -0.07
     BU
    -0.06
     Shows
    -0.06
     Reference
    -0.06
    одейств
    -0.06
    отв
    -0.06
     DataView
    -0.06
    POSITIVE LOGITS
     효
    0.06
    .group
    0.06
    ‬
    0.06
     shampoo
    0.06
    elsey
    0.06
     Harrison
    0.05
    主任
    0.05
    髪
    0.05
     energie
    0.05
    760
    0.05
    Act Density 0.000%

    No Known Activations