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

    Neuronpedia

    INDEX
    Explanations

    Tank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    末
    -0.08
    	glog
    -0.07
     Ridge
    -0.07
     Epstein
    -0.07
     Morris
    -0.07
    布
    -0.07
    晴
    -0.07
     เด
    -0.07
    ется
    -0.06
    TableRow
    -0.06
    POSITIVE LOGITS
     tank
    0.19
     Tank
    0.16
     tanks
    0.16
    -tank
    0.13
    tank
    0.13
    Tank
    0.12
     Tanks
    0.11
    ank
    0.09
     tanker
    0.09
    ANK
    0.09
    Act Density 0.003%

    No Known Activations