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

    Neuronpedia

    INDEX
    Explanations

    listing items connected by 'and' or '&'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ※
    0.81
     по
    0.71
    など
    0.68
    house
    0.67
    lands
    0.66
    ্যারি
    0.64
    가
    0.64
    ה
    0.64
    বী
    0.64
    が
    0.64
    POSITIVE LOGITS
    amp
    1.15
    StarGo
    0.96
     foremost
    0.86
    eacute
    0.84
    rsquo
    0.84
    ndash
    0.82
    Amp
    0.81
     sundry
    0.81
    rews
    0.81
     desist
    0.81
    Act Density 0.578%

    No Known Activations