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

    Neuronpedia

    INDEX
    Explanations

    recommending best options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ษัท
    0.44
     máme
    0.44
     这是
    0.43
     sAlarm
    0.41
     داریم
    0.41
    вости
    0.41
    TacToe
    0.41
     ይታ
    0.41
     tenemos
    0.41
    ваме
    0.41
    POSITIVE LOGITS
     Consider
    0.86
    Consider
    0.77
     consider
    0.74
    consider
    0.69
    考虑
    0.68
     Probably
    0.68
     probably
    0.65
     Unless
    0.64
     If
    0.64
    If
    0.63
    Act Density 0.001%

    No Known Activations