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

    Neuronpedia

    INDEX
    Explanations

    Naval warfare/ship attacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TableColumn
    -0.07
     Ama
    -0.07
     fb
    -0.06
    카
    -0.06
    بوب
    -0.06
    ट
    -0.06
     земля
    -0.06
     Hussein
    -0.06
    urst
    -0.06
     Ga
    -0.06
    POSITIVE LOGITS
    Caught
    0.07
     transmit
    0.06
    ayscale
    0.06
    Fetching
    0.06
    .elasticsearch
    0.06
    tier
    0.06
     scarc
    0.06
     extreme
    0.06
    _lstm
    0.06
     configuring
    0.06
    Act Density 0.015%

    No Known Activations