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

    Neuronpedia

    INDEX
    Explanations

    United States, HOME to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jske
    0.84
     KING
    0.76
    KING
    0.72
     ہاں
    0.71
     AQ
    0.71
     AMI
    0.70
    <unused2139>
    0.69
     அதிகரித்து
    0.69
    句話
    0.68
    न्हे
    0.68
    POSITIVE LOGITS
     ശു
    0.68
     détach
    0.67
     Shash
    0.64
     Stal
    0.64
     Shukla
    0.63
    plates
    0.63
    电路
    0.62
    optim
    0.62
    Optim
    0.61
     easily
    0.61
    Act Density 0.046%

    No Known Activations