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

    Neuronpedia

    INDEX
    Explanations

    also, again, or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    하였다
    0.40
    क्‍त
    0.40
    等が
    0.40
     रोज़
    0.39
    കൊണ്ട്
    0.38
    खनऊ
    0.38
    Jährige
    0.38
     изпол
    0.38
     जहाज़
    0.38
    ኾ
    0.38
    POSITIVE LOGITS
    也
    0.42
    also
    0.42
     ​​
    0.40
     also
    0.37
    ও
    0.35
    อีก
    0.34
    again
    0.34
    <0xC2>
    0.33
    Also
    0.33
     Also
    0.32
    Act Density 0.154%

    No Known Activations