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

    Neuronpedia

    INDEX
    Explanations

    equipped

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bonds
    -0.08
     aliens
    -0.08
     chí
    -0.07
     tuna
    -0.07
     Shift
    -0.07
     cân
    -0.06
    -render
    -0.06
     raping
    -0.06
     SHIFT
    -0.06
     rape
    -0.06
    POSITIVE LOGITS
     equipped
    0.11
    -equipped
    0.10
     equip
    0.08
     equipe
    0.07
     adequately
    0.06
     Emp
    0.06
    كييف
    0.06
     outf
    0.06
     Armed
    0.06
     prowess
    0.06
    Act Density 0.012%

    No Known Activations