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

    Neuronpedia

    INDEX
    Explanations

    purpose or intention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    9
    1.07
    RI
    1.05
    Tasty
    1.01
    8
    1.01
    TRO
    1.00
    TA
    0.99
    back
    0.95
    0
    0.95
    night
    0.93
    und
    0.93
    POSITIVE LOGITS
     purpose
    1.55
     purposes
    1.19
     Zweck
    1.16
     Purposes
    1.09
     நோக்க
    1.09
     목적
    1.05
     propósito
    1.02
     amaç
    1.00
     उद्देश्य
    0.99
     intention
    0.98
    Act Density 0.504%

    No Known Activations