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

    Neuronpedia

    INDEX
    Explanations

    matrix notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    0.84
     montagna
    0.81
     montaña
    0.80
     শব্দ
    0.78
     भीड़
    0.77
     comun
    0.76
     molti
    0.75
     quei
    0.75
    presa
    0.74
     는
    0.73
    POSITIVE LOGITS
    0.74
    ile
    0.73
    ar
    0.72
    ase
    0.72
    and
    0.71
    એ
    0.69
     Gant
    0.68
    weighted
    0.66
     walnuts
    0.66
    aid
    0.66
    Act Density 0.001%

    No Known Activations