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

    Neuronpedia

    INDEX
    Explanations

    drawings and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    personas
    0.50
    ਕਾਰ
    0.49
    цент
    0.41
     infantil
    0.41
    बच्चों
    0.40
    زار
    0.40
    小
    0.39
    Де
    0.39
    inz
    0.38
    ёнок
    0.38
    POSITIVE LOGITS
     सलाद
    0.46
    addo
    0.40
    toISOString
    0.40
     Harlow
    0.39
     rival
    0.37
     তাৎ
    0.37
     Yosemite
    0.37
    UseVisualStyle
    0.37
    getState
    0.36
    နည်း
    0.36
    Act Density 0.001%

    No Known Activations