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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     synth
    -0.07
    导致
    -0.07
    INED
    -0.07
     farms
    -0.06
     문제
    -0.06
     letech
    -0.06
    translator
    -0.06
     consists
    -0.06
     plunder
    -0.06
    verse
    -0.06
    POSITIVE LOGITS
    _article
    0.07
    )a
    0.07
     strs
    0.06
    ★
    0.06
     vf
    0.06
    .ColumnStyle
    0.06
     airflow
    0.06
     Puppy
    0.06
    _TE
    0.06
    (tk
    0.06
    Act Density 0.075%

    No Known Activations