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

    Neuronpedia

    INDEX
    Explanations

    agreeing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.09
    -led
    -0.08
    وپ
    -0.07
     saldo
    -0.07
     �
    -0.07
    Been
    -0.07
     وما
    -0.06
    --------------↵
    -0.06
     enumerated
    -0.06
    "L
    -0.06
    POSITIVE LOGITS
    great
    0.06
    Combine
    0.06
     great
    0.06
    _storage
    0.06
    steam
    0.06
    -delete
    0.06
    /container
    0.06
     Inputs
    0.05
    .Generate
    0.05
    [:-
    0.05
    Act Density 0.018%

    No Known Activations