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

    Neuronpedia

    INDEX
    Explanations

    fresh instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    electron
    0.58
    enclose
    0.52
    interfaces
    0.51
    ar
    0.50
    Ultimate
    0.49
    Left
    0.49
    Mercury
    0.49
    iable
    0.49
    *}$
    0.48
    XMLHttpRequest
    0.48
    POSITIVE LOGITS
     acara
    0.55
     edition
    0.54
     laughing
    0.52
     saraf
    0.52
     is
    0.52
     appare
    0.50
     wanita
    0.50
     consumption
    0.50
     feas
    0.50
     benar
    0.49
    Act Density 0.000%

    No Known Activations