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

    Neuronpedia

    INDEX
    Explanations

    businesses and height is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    志愿
    0.41
    alarının
    0.40
     závod
    0.39
    adiene
    0.38
     সৌজন্য
    0.37
    uldig
    0.37
    שרה
    0.37
     porosity
    0.36
    ందు
    0.36
     Loose
    0.36
    POSITIVE LOGITS
     tuli
    0.41
     reformers
    0.39
     revelations
    0.39
     હતી
    0.38
    するので
    0.37
    アドレス
    0.37
     plung
    0.37
    reform
    0.36
     Reforms
    0.36
    тым
    0.35
    Act Density 0.012%

    No Known Activations