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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puja
    0.47
    کروچ
    0.46
     dumpster
    0.46
    𝕞
    0.45
     superblock
    0.45
     monopolies
    0.44
     totalling
    0.44
    وڑا
    0.44
     hoof
    0.43
    িনবার্গ
    0.43
    POSITIVE LOGITS
    ៕
    1.03
     குறிப்பிடத்தக்க
    0.64
    <eos>
    0.56
    
    0.50
     देखना
    0.49
    ©
    0.49
    ]]
    0.49
     धन्यवाद
    0.47
    }
    0.47
    😊
    0.46
    Act Density 0.209%

    No Known Activations