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

    Neuronpedia

    INDEX
    Explanations

    expectations or prerequisites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ara
    0.45
     in
    0.44
    ann
    0.42
    erden
    0.41
    oyu
    0.41
    aud
    0.41
     entering
    0.40
    Ü
    0.40
    igheter
    0.39
    lic
    0.39
    POSITIVE LOGITS
     continueRoutine
    0.49
     desempen
    0.46
    getRedTeam
    0.46
     повин
    0.45
     Aufgrund
    0.45
     odpor
    0.44
    segaretro
    0.44
     contradd
    0.44
     Wilber
    0.44
     verily
    0.44
    Act Density 0.001%

    No Known Activations