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

    Neuronpedia

    INDEX
    Explanations

    more than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bashing
    0.68
     CAUSED
    0.65
    کروچ
    0.63
    <unused628>
    0.63
     哦
    0.62
     ഹോളി
    0.61
    ൮
    0.61
    atoti
    0.60
    <unused915>
    0.60
     Darüber
    0.60
    POSITIVE LOGITS
    0.64
      
    0.59
    <unused60>
    0.55
       
    0.53
    0.49
    ↵
    0.47
    <0xE3>
    0.46
    <0xC2>
    0.46
        
    0.45
           
    0.41
    Act Density 1.311%

    No Known Activations