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

    Neuronpedia

    INDEX
    Explanations

    I suppose or assume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大好き
    0.37
    热爱
    0.37
     கழக
    0.35
     ધર
    0.32
    힝
    0.32
     swojej
    0.31
     PRET
    0.31
     රස
    0.30
    ခံ
    0.30
     tumbuh
    0.30
    POSITIVE LOGITS
     recommend
    0.45
     expect
    0.43
     suspect
    0.39
     advise
    0.39
     anticipate
    0.39
     noted
    0.38
     presume
    0.37
     assume
    0.37
     क्रमशः
    0.34
     doubt
    0.34
    Act Density 0.011%

    No Known Activations