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

    Neuronpedia

    INDEX
    Explanations

    darling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.57
    through
    0.53
    NOP
    0.52
    N
    0.50
    Z
    0.49
    SR
    0.48
    L
    0.47
    OT
    0.46
    way
    0.46
    low
    0.46
    POSITIVE LOGITS
     bhavati
    0.57
     ইচ্ছা
    0.46
    嵐
    0.46
     hikes
    0.45
     attains
    0.45
     optimality
    0.45
     elevates
    0.45
     adhik
    0.45
     caravans
    0.44
    >..\
    0.43
    Act Density 0.003%

    No Known Activations