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

    Neuronpedia

    INDEX
    Explanations

    Aliens, smell, thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
                        
    0.71
    াবণ
    0.67
    ปล
    0.59
                         
    0.58
    اية
    0.58
     Rave
    0.57
     fourth
    0.57
     eighth
    0.57
     ख्
    0.56
     Graves
    0.56
    POSITIVE LOGITS
     tensorflow
    0.57
                  
    0.57
     సంగీ
    0.55
    蜒
    0.55
    <0x1D>
    0.54
     raconte
    0.52
    䣰
    0.52
    伦
    0.52
    .............
    0.52
     वातावरण
    0.52
    Act Density 0.008%

    No Known Activations