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

    Neuronpedia

    INDEX
    Explanations

    helping others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    än
    0.50
    isierung
    0.46
    opy
    0.44
    рование
    0.42
    सभी
    0.42
    Gender
    0.41
    Ex
    0.41
    opies
    0.41
    et
    0.40
    ety
    0.40
    POSITIVE LOGITS
     Helping
    0.43
     этому
    0.41
     Katalog
    0.41
     Workshops
    0.40
     Missions
    0.40
     Fundraising
    0.40
     Комп
    0.40
     $$$
    0.40
     রোধ
    0.39
    不由
    0.39
    Act Density 0.000%

    No Known Activations