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

    Neuronpedia

    INDEX
    Explanations

    transgender/intersex conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spot
    -0.08
     happ
    -0.06
     spots
    -0.06
     rubbed
    -0.06
     голови
    -0.06
     lobbyist
    -0.06
     pint
    -0.06
     months
    -0.06
     худож
    -0.06
     Harbor
    -0.06
    POSITIVE LOGITS
     إذ
    0.07
    rastructure
    0.06
    ención
    0.06
    ¯¯¯¯
    0.06
    aises
    0.06
    ../
    0.06
    ной
    0.06
    '];
↵
    0.06
     Bunny
    0.06
    (Filter
    0.06
    Act Density 0.009%

    No Known Activations