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

    Neuronpedia

    INDEX
    Explanations

    humanitarian, medical aid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stitch
    -0.09
     revolve
    -0.09
     fix
    -0.08
     outperform
    -0.08
    拼
    -0.08
     horsepower
    -0.08
     join
    -0.08
    �
    -0.08
    .motor
    -0.07
     finish
    -0.07
    POSITIVE LOGITS
     humanitarian
    0.11
     neutrality
    0.11
     Neutral
    0.11
     massac
    0.10
     Protected
    0.10
     гуман
    0.10
     massacre
    0.10
     युद्ध
    0.10
     Hospital
    0.10
     savaş
    0.10
    Act Density 0.061%

    No Known Activations