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

    Neuronpedia

    INDEX
    Explanations

    building or to build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.86
    egin
    0.79
    doc
    0.78
    rule
    0.76
    sample
    0.73
    Determ
    0.72
    bb
    0.72
    tech
    0.72
    san
    0.72
     Determines
    0.71
    POSITIVE LOGITS
     contrasting
    0.84
    䀓
    0.82
     livre
    0.79
     bodyguard
    0.78
     euthanasia
    0.78
     totalitarian
    0.77
     día
    0.76
     biasa
    0.75
     reação
    0.75
     speedometer
    0.75
    Act Density 0.001%

    No Known Activations