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

    Neuronpedia

    INDEX
    Explanations

    dangerous voltages arc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.49
     lembra
    0.48
    s
    0.48
     naturais
    0.48
    }=
    0.47
     giphy
    0.47
     strán
    0.46
     conteú
    0.46
    }|=
    0.46
     congén
    0.46
    POSITIVE LOGITS
    Malaysia
    0.45
    oprene
    0.44
    परेट
    0.43
    umbing
    0.41
    getBean
    0.41
    াণিত
    0.41
    annte
    0.41
    ationen
    0.41
    াপনের
    0.41
    lemy
    0.41
    Act Density 0.001%

    No Known Activations