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

    Neuronpedia

    INDEX
    Explanations

    helpline .org

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     portada
    0.83
     jardins
    0.80
     Além
    0.79
     JPA
    0.79
     Revista
    0.78
     realidade
    0.77
     اكتب
    0.75
     integrar
    0.75
     tabular
    0.74
     jardim
    0.74
    POSITIVE LOGITS
    uasion
    0.73
     Frobenius
    0.67
    혔
    0.63
    भीर
    0.62
     half
    0.61
    ारस
    0.59
     Half
    0.58
    Half
    0.57
    었던
    0.57
    దారు
    0.57
    Act Density 0.010%

    No Known Activations