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

    Neuronpedia

    INDEX
    Explanations

    not alone, strength, valid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mr
    0.44
     moderately
    0.42
     prospect
    0.42
     grinning
    0.42
     After
    0.41
     rol
    0.41
     looms
    0.40
     ম্যা
    0.40
     shirtless
    0.39
     after
    0.38
    POSITIVE LOGITS
     파인더
    0.49
     bukanlah
    0.45
     absolutamente
    0.45
     괜찮
    0.44
    🦠
    0.43
    Heter
    0.42
     deserve
    0.42
     layak
    0.42
    伟大
    0.42
    ногие
    0.41
    Act Density 0.182%

    No Known Activations