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

    Neuronpedia

    INDEX
    Explanations

    batteries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     battery
    -1.66
     batteries
    -1.66
     Battery
    -1.64
     BATTERY
    -1.56
    Battery
    -1.52
    battery
    -1.52
     Batteries
    -1.48
     batterie
    -1.34
     Majefty
    -1.33
     $_"
    -1.32
    POSITIVE LOGITS
    .
    0.96
    ,
    0.91
     (
    0.91
     
    0.89
    ↵↵
    0.85
     and
    0.81
     for
    0.81
     in
    0.81
     I
    0.80
     of
    0.79
    Act Density 0.071%

    No Known Activations