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

    Neuronpedia

    INDEX
    Explanations

    if followed by pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perhaps
    0.53
    Perhaps
    0.51
     entrap
    0.49
     Perhaps
    0.48
     indeed
    0.44
    そのような
    0.44
    perhaps
    0.43
     coloro
    0.43
     madness
    0.42
    하였
    0.42
    POSITIVE LOGITS
     खूब
    0.50
     mom
    0.47
    uk
    0.42
     didn
    0.42
    我说
    0.42
     два
    0.42
     জিনি
    0.42
     हुन्छ
    0.42
     kid
    0.42
    我們先
    0.42
    Act Density 0.023%

    No Known Activations