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

    Neuronpedia

    INDEX
    Explanations

    the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모습
    0.35
    ρίς
    0.34
    romino
    0.34
    wer
    0.33
    โมง
    0.33
    ChoiceItemLayout
    0.31
     Nähe
    0.31
     나머
    0.31
    ؒ
    0.31
    StarObject
    0.30
    POSITIVE LOGITS
     the
    0.80
    the
    0.76
     את
    0.66
    sthe
    0.59
    文件的
    0.57
    의
    0.56
    ங்களின்
    0.55
    την
    0.55
     την
    0.55
     τὴν
    0.55
    Act Density 0.794%

    No Known Activations