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

    Neuronpedia

    INDEX
    Explanations

    villain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .energy
    -0.07
     kro
    -0.07
     entry
    -0.07
     importantes
    -0.06
     ""
    -0.06
     UIResponder
    -0.06
     ++)
    -0.06
     东
    -0.06
    วไป
    -0.06
     ++↵
    -0.06
    POSITIVE LOGITS
     villain
    0.08
     sculpture
    0.08
     villains
    0.08
     Vill
    0.07
    数学
    0.06
    _setopt
    0.06
    �
    0.06
     Backpack
    0.06
    chapter
    0.06
    ii
    0.06
    Act Density 0.005%

    No Known Activations