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

    Neuronpedia

    INDEX
    Explanations

    honesty and honor related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     long
    0.78
     ISA
    0.69
     crowds
    0.66
     dép
    0.65
     LONG
    0.65
     citizen
    0.64
     symptom
    0.64
     metam
    0.64
     stellar
    0.63
     MSCI
    0.63
    POSITIVE LOGITS
    oring
    1.70
    ored
    1.56
    orable
    1.52
    ors
    1.50
    ouring
    1.42
    oured
    1.42
    ores
    1.26
    oration
    1.26
    ORS
    1.24
    orar
    1.24
    Act Density 0.026%

    No Known Activations