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

    Neuronpedia

    INDEX
    Explanations

    understanding and prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    собенно
    0.42
     जेव्हा
    0.41
    क्व
    0.40
    Если
    0.40
    तें
    0.40
     যেদিন
    0.40
    ED
    0.39
     उनमें
    0.39
    Jeśli
    0.39
    ždy
    0.38
    POSITIVE LOGITS
     존재하는
    0.43
    舒服
    0.43
     sightseeing
    0.42
    杫
    0.41
     தேர்வு
    0.40
    爽
    0.40
     search
    0.40
     Estamos
    0.40
     Kennt
    0.39
    军队
    0.39
    Act Density 0.002%

    No Known Activations