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

    Neuronpedia

    INDEX
    Explanations

    gang followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Darwin
    0.40
     Darwin
    0.39
     can
    0.37
     Bewegung
    0.36
     തോ
    0.36
    ffe
    0.36
     Alice
    0.35
     jari
    0.35
     ric
    0.35
     Sebastian
    0.35
    POSITIVE LOGITS
     Gang
    0.59
     gang
    0.57
     गंग
    0.53
    Gang
    0.52
    gang
    0.50
     gangs
    0.46
     गैंग
    0.46
    izarra
    0.42
    stered
    0.41
    apur
    0.40
    Act Density 0.002%

    No Known Activations