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

    Neuronpedia

    INDEX
    Explanations

    safely granted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Least
    0.51
     riforma
    0.50
    𒋼
    0.49
    𒈾
    0.47
    没有人
    0.46
     dólares
    0.45
    亏
    0.45
     नं
    0.44
    GUAR
    0.44
     produzione
    0.43
    POSITIVE LOGITS
    Pick
    0.45
     itali
    0.38
    ettings
    0.38
    ď
    0.38
     lugs
    0.37
    ��
    0.37
    興味
    0.37
    <0x0B>
    0.37
    lobe
    0.36
    ポンプ
    0.36
    Act Density 24.055%

    No Known Activations