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

    Neuronpedia

    INDEX
    Explanations

    relaxation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.68
    iële
    -0.62
    othes
    -0.60
    conia
    -0.59
    ardized
    -0.59
    nals
    -0.59
    corpions
    -0.59
    PerformLayout
    -0.58
    reportWebVitals
    -0.58
     Rig
    -0.57
    POSITIVE LOGITS
    ніципалі
    0.49
     man
    0.47
     يتيمه
    0.46
    Responses
    0.43
    responses
    0.41
     response
    0.41
    これも
    0.40
    ReadByte
    0.40
    DESCRIPTOR
    0.40
    లాలు
    0.40
    Act Density 0.002%

    No Known Activations