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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sandra
    -0.07
    .AUTO
    -0.07
    upro
    -0.07
    _AdjustorThunk
    -0.07
    essim
    -0.06
     POLIT
    -0.06
    Beauty
    -0.06
    _backup
    -0.06
     Kuwait
    -0.06
     harbor
    -0.06
    POSITIVE LOGITS
    mer
    0.06
     кишеч
    0.06
     ag
    0.06
    891
    0.06
     흔
    0.06
    ]*(
    0.06
    ;text
    0.06
     आम
    0.06
     ulcer
    0.06
     pł
    0.06
    Act Density 0.003%

    No Known Activations