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

    Neuronpedia

    INDEX
    Explanations

    similarity and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    昛
    0.63
     또한
    0.54
     ಮೂಲಕ
    0.54
     குடியிருப்ப
    0.52
    ে
    0.52
    䆔
    0.51
    मूर्ति
    0.50
    敚
    0.50
     سننے
    0.49
    贰
    0.49
    POSITIVE LOGITS
     d
    0.53
    ic
    0.49
     h
    0.49
     lib
    0.48
     list
    0.48
    0.47
    &
    0.47
     lab
    0.47
     label
    0.46
     letter
    0.46
    Act Density 0.003%

    No Known Activations