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

    Neuronpedia

    INDEX
    Explanations

    nuances introducing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _)
    0.83
     }}$.
    0.80
     ၊
    0.77
    \'{
    0.76
     !,
    0.74
     XNUMX
    0.73
    ！）
    0.73
     ~,
    0.73
     」
    0.73
     [])
    0.71
    POSITIVE LOGITS
    :
    5.71
    :**
    4.64
    :*
    4.55
    :"
    4.54
    :</
    4.50
    ：
    4.48
    :}
    4.42
    :\
    4.33
    :”
    4.24
    :",
    4.17
    Act Density 7.450%

    No Known Activations