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

    Neuronpedia

    INDEX
    Explanations

    free play, demo, practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.59
    Counc
    0.59
    四
    0.59
    us
    0.54
    ，
    0.54
    Wild
    0.52
    :
    0.51
    <0xE7>
    0.50
    Mich
    0.50
    स
    0.49
    POSITIVE LOGITS
    İL
    0.63
     fraudulently
    0.58
    এসসি
    0.57
    వడం
    0.57
     Ευ
    0.56
     výro
    0.55
     ভবন
    0.55
     Printable
    0.55
    ")),
    0.54
     производстве
    0.54
    Act Density 0.004%

    No Known Activations