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

    Neuronpedia

    INDEX
    Explanations

    adult child relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ph
    0.47
     mauvais
    0.46
    Tenemos
    0.46
     validate
    0.43
     Bla
    0.42
     LEM
    0.41
    ിത്ര
    0.40
     niece
    0.40
    ាតុ
    0.40
     restring
    0.40
    POSITIVE LOGITS
    uğu
    0.50
     sahaja
    0.47
    ığı
    0.47
    距离
    0.44
    adas
    0.44
    aron
    0.44
    uk
    0.43
    的总
    0.43
    υτό
    0.42
    uan
    0.42
    Act Density 0.001%

    No Known Activations