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

    Neuronpedia

    INDEX
    Explanations

    combat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vtx
    -0.07
     Tues
    -0.06
     están
    -0.06
     skup
    -0.06
     fres
    -0.06
     tablespoon
    -0.06
     αξ
    -0.06
     Sunset
    -0.06
     tapi
    -0.06
     ون
    -0.06
    POSITIVE LOGITS
     combat
    0.09
     Combat
    0.09
    War
    0.07
    Hit
    0.07
    Combat
    0.07
     Warfare
    0.07
     Crud
    0.07
    斗
    0.07
    fighters
    0.07
     Kill
    0.07
    Act Density 0.005%

    No Known Activations