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

    Neuronpedia

    INDEX
    Explanations

    With

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (TRUE
    -0.07
     intensely
    -0.06
     barley
    -0.06
     trom
    -0.06
    iov
    -0.06
    _player
    -0.06
    niejs
    -0.06
     ipsum
    -0.06
    before
    -0.06
     avant
    -0.06
    POSITIVE LOGITS
    nds
    0.07
     hubby
    0.07
     고객
    0.07
    .NewLine
    0.06
    Respond
    0.06
     UNITED
    0.06
     unilateral
    0.06
     Couldn
    0.06
     вип
    0.06
    LENGTH
    0.06
    Act Density 0.016%

    No Known Activations