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

    Neuronpedia

    INDEX
    Explanations

    starring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     updatedAt
    -0.07
    banana
    -0.06
     flavored
    -0.06
     cleanup
    -0.06
     spa
    -0.06
     приня
    -0.06
    ]])↵↵
    -0.06
    female
    -0.06
     Gate
    -0.06
    amide
    -0.06
    POSITIVE LOGITS
     extra
    0.07
     underground
    0.06
    lected
    0.06
     revolves
    0.06
     ".
    0.06
    냥
    0.06
     dışında
    0.06
     созда
    0.06
     AUT
    0.06
     invoice
    0.06
    Act Density 0.005%

    No Known Activations