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

    Neuronpedia

    INDEX
    Explanations

    organization acronyms and standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seres
    -0.74
     bring
    -0.74
    ویزی
    -0.74
     vaiz
    -0.74
     contratar
    -0.71
     Woodrow
    -0.71
     Imagery
    -0.71
    raven
    -0.70
     Ashby
    -0.69
     Mädchen
    -0.69
    POSITIVE LOGITS
    Standard
    0.86
     Standard
    0.83
     Eaton
    0.83
     Climat
    0.79
     LIM
    0.79
     nineteenth
    0.76
     ASSOCIATION
    0.76
     dorso
    0.76
     стандарт
    0.76
     STANDARD
    0.75
    Act Density 0.012%

    No Known Activations