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

    Neuronpedia

    INDEX
    Explanations

    chatbots and conversation comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ្នុង
    0.49
     이용하여
    0.44
     intelekt
    0.43
    ethoscope
    0.42
    inFile
    0.42
     چلے
    0.41
     συνα
    0.41
     manto
    0.41
    दमी
    0.41
     प्रेरणात्मक
    0.41
    POSITIVE LOGITS
     is
    0.51
     X
    0.47
    '
    0.46
    ?
    0.46
     Please
    0.46
    」
    0.46
    </div>
    0.45
    es
    0.45
     m
    0.45
     Option
    0.45
    Act Density 0.001%

    No Known Activations