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

    Neuronpedia

    INDEX
    Explanations

    professionalisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entferne
    1.84
     aplatis
    1.77
     innych
    1.72
     jotka
    1.72
     suivants
    1.70
     dificuldades
    1.70
     mesmos
    1.69
     poblaciones
    1.67
     zmian
    1.66
     apuestas
    1.66
    POSITIVE LOGITS
    1.99
    5
    1.72
    1
    1.70
    2
    1.63
    8
    1.62
    3
    1.59
    9
    1.59
    6
    1.58
     "
    1.57
    0
    1.56
    Act Density 0.646%

    No Known Activations