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

    Neuronpedia

    INDEX
    Explanations

    Hair removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autonomous
    -0.09
     brethren
    -0.08
     wealthy
    -0.08
     bomber
    -0.08
     பக
    -0.08
    련
    -0.08
     decks
    -0.08
     aura
    -0.08
     broadcast
    -0.08
     generosity
    -0.08
    POSITIVE LOGITS
     Zie
    0.09
     Removes
    0.09
     удалить
    0.09
     Removing
    0.08
     Entfer
    0.08
     ang
    0.08
     dermat
    0.08
     remover
    0.08
     잡
    0.08
     floss
    0.08
    Act Density 0.012%

    No Known Activations