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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs or assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     “[
    0.83
     “…
    0.82
     “‘
    0.82
     ‘’
    0.80
     "...
    0.79
    /"
    0.75
    “[
    0.74
    /'
    0.74
     “”
    0.71
    ‘’
    0.70
    POSITIVE LOGITS
     গ্রহণ
    0.51
     filmes
    0.51
     tĩnh
    0.50
    <unused2174>
    0.49
     छह
    0.49
     tamu
    0.48
     departamentos
    0.48
     provoquer
    0.47
    させていただきます
    0.47
     মাহ
    0.46
    Act Density 0.929%

    No Known Activations