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

    Neuronpedia

    INDEX
    Explanations

    Important notes/disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.41
    ."
    0.40
    ':
    0.39
    .'
    0.38
    bench
    0.38
    1
    0.38
    beat
    0.37
    canvas
    0.37
    Facade
    0.37
    -
    0.37
    POSITIVE LOGITS
     there
    0.84
    there
    0.78
     There
    0.76
     यह
    0.70
    この
    0.70
     dieser
    0.69
     یہ
    0.68
     Only
    0.67
     هذا
    0.65
    There
    0.65
    Act Density 0.035%

    No Known Activations