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

    Neuronpedia

    INDEX
    Explanations

    shifting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -select
    -0.07
    영상
    -0.06
     hran
    -0.06
    Whenever
    -0.06
    .room
    -0.06
     summ
    -0.06
    tabs
    -0.06
     stride
    -0.06
     hybrids
    -0.06
    “To
    -0.06
    POSITIVE LOGITS
    วง
    0.07
    .minLength
    0.07
    onec
    0.06
     уд
    0.06
    ¨¨
    0.06
     GRAT
    0.06
     sulfate
    0.06
    .Pull
    0.06
     assembler
    0.06
     //================================================================
    0.06
    Act Density 0.014%

    No Known Activations