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

    Neuronpedia

    INDEX
    Explanations

    different sleep durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.55
    nt
    0.50
     rid
    0.50
    ale
    0.49
    EG
    0.49
     strani
    0.48
    ley
    0.48
    lie
    0.47
    nete
    0.47
    IE
    0.47
    POSITIVE LOGITS
    ताच
    0.56
    таў
    0.51
    inairement
    0.50
    𝘭
    0.50
     Ouvrard
    0.50
     खुराक
    0.49
    𝓭
    0.48
    充电
    0.47
    遶
    0.46
    біць
    0.45
    Act Density 0.000%

    No Known Activations