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

    Neuronpedia

    INDEX
    Explanations

    company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laborers
    1.71
     laborer
    1.66
     senseless
    1.63
     labourers
    1.63
     וא
    1.62
    را
    1.59
    жде
    1.59
    ীন্দ্র
    1.56
     וכ
    1.53
     homegrown
    1.53
    POSITIVE LOGITS
    en
    2.05
    wares
    1.94
    enc
    1.78
    te
    1.73
    alarm
    1.70
    wide
    1.69
    vad
    1.69
    թ
    1.66
    espoir
    1.65
    ள்ள
    1.63
    Act Density 0.161%

    No Known Activations