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
     Rockefeller
    -0.08
    efeller
    -0.08
    _RULE
    -0.07
    -rule
    -0.06
    óln
    -0.06
     arranged
    -0.06
    _ll
    -0.06
     Wald
    -0.06
     seals
    -0.06
     Wid
    -0.06
    POSITIVE LOGITS
     combat
    0.12
     Combat
    0.10
    combat
    0.10
    Combat
    0.09
    bat
    0.08
    ob
    0.08
    cab
    0.08
    -------↵↵
    0.07
    -addon
    0.07
    斗
    0.07
    Act Density 0.005%

    No Known Activations