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

    Neuronpedia

    INDEX
    Explanations

    then, commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    formData
    -0.06
    cu
    -0.06
     �
    -0.06
    _management
    -0.06
    Merge
    -0.06
    iseconds
    -0.06
    emin
    -0.06
     smart
    -0.06
    原来
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    पत
    0.07
    ư
    0.06
    DonaldTrump
    0.06
     ACM
    0.06
     ffm
    0.06
     pleas
    0.06
     Pill
    0.06
    _ARCH
    0.06
    _VALUE
    0.06
    -route
    0.06
    Act Density 0.149%

    No Known Activations