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

    Neuronpedia

    INDEX
    Explanations

    looking for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    সভাপতি
    0.42
     drawable
    0.40
     smack
    0.39
     ditulis
    0.38
     judgmental
    0.38
     connects
    0.38
     departures
    0.38
    studied
    0.38
    sommets
    0.38
     riffs
    0.37
    POSITIVE LOGITS
     searching
    1.28
    searching
    1.12
     Searching
    1.07
     trying
    1.05
     search
    0.98
     enqu
    0.97
     mencari
    0.96
    Searching
    0.96
     inquire
    0.91
     investigating
    0.89
    Act Density 0.000%

    No Known Activations