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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA National

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ▫
    2.06
     што
    1.76
     polyvinyl
    1.69
     meandering
    1.69
     nende
    1.65
     verlie
    1.65
    ようになる
    1.64
     Tolkien
    1.63
     hiring
    1.61
     fallen
    1.60
    POSITIVE LOGITS
    ly
    1.74
    as
    1.57
    ور
    1.53
    ive
    1.50
    ни
    1.48
    ain
    1.47
    і
    1.47
     нада
    1.41
    est
    1.41
     microsomal
    1.41
    Act Density 0.008%

    No Known Activations