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

    Neuronpedia

    INDEX
    Explanations

    botox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    央
    -0.08
     dobb
    -0.08
    ष
    -0.08
     Luxembourg
    -0.07
     Rear
    -0.07
    .index
    -0.07
     marr
    -0.07
     सम्म
    -0.07
     lez
    -0.07
    uffix
    -0.07
    POSITIVE LOGITS
     препараты
    0.09
     Cosmetic
    0.09
     cosmetic
    0.08
     отключ
    0.08
     വൈറ
    0.08
    -famous
    0.08
     Botox
    0.08
    -fired
    0.08
     извест
    0.08
     inhibit
    0.08
    Act Density 0.001%

    No Known Activations