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

    Neuronpedia

    INDEX
    Explanations

    military conflicts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ~
    -0.08
    uke
    -0.07
    �
    -0.07
    ］
    -0.06
     Bain
    -0.06
     optarg
    -0.06
     <<<
    -0.06
    ap
    -0.06
    oň
    -0.06
    _ix
    -0.06
    POSITIVE LOGITS
     eighty
    0.07
     муницип
    0.06
    라피
    0.06
    angent
    0.06
    licht
    0.06
     knocks
    0.06
     explodes
    0.06
    launcher
    0.06
    	↵	↵	↵	↵
    0.06
     وب
    0.06
    Act Density 0.014%

    No Known Activations