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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Roy
    -0.06
     DAO
    -0.06
    KS
    -0.06
     certain
    -0.06
     REMOVE
    -0.06
    ACIÓN
    -0.06
    candidates
    -0.06
    acter
    -0.06
    -0.06
    敦
    -0.06
    POSITIVE LOGITS
    >)
    0.07
     disp
    0.06
     男
    0.06
    _BITS
    0.06
    /Input
    0.06
    )p
    0.06
     nursery
    0.06
    ‘
    0.06
    !")↵
    0.06
    �
    0.06
    Act Density 0.203%

    No Known Activations