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

    Neuronpedia

    INDEX
    Explanations

    of others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aspects
    0.64
     के
    0.63
     की
    0.63
     Attempts
    0.62
     instances
    0.62
    มีการ
    0.61
     use
    0.61
     параметры
    0.60
     characteristics
    0.60
    pesar
    0.60
    POSITIVE LOGITS
     bygone
    0.78
     yester
    0.74
     colonialism
    0.71
    那些
    0.69
     diejenigen
    0.68
    Others
    0.67
     adolescence
    0.66
    Those
    0.65
    甲烷
    0.65
     LTP
    0.65
    Act Density 0.135%

    No Known Activations