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

    Neuronpedia

    INDEX
    Explanations

    quoted text followed by 't'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     binary
    0.54
     src
    0.50
     exchangers
    0.48
     contrived
    0.48
     elution
    0.47
     Eshelby
    0.47
     comprising
    0.46
     neglected
    0.44
     arcs
    0.44
     hose
    0.44
    POSITIVE LOGITS
    r
    0.56
    swear
    0.54
    land
    0.54
    lim
    0.52
    quired
    0.52
    fuel
    0.52
    lost
    0.52
    rent
    0.51
    ruit
    0.51
    vaal
    0.51
    Act Density 0.004%

    No Known Activations