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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Airport
    -0.06
     svém
    -0.06
     Mobile
    -0.06
     segment
    -0.06
    �
    -0.06
     neighbouring
    -0.06
    .timing
    -0.06
    galement
    -0.06
    _piece
    -0.06
    7
    -0.06
    POSITIVE LOGITS
     shuffle
    0.07
    ーフ
    0.07
     하지
    0.06
    grab
    0.06
    .borrow
    0.06
     nějaký
    0.06
    mma
    0.06
     enlarge
    0.06
     Achilles
    0.06
    dorf
    0.06
    Act Density 0.000%

    No Known Activations