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

    Neuronpedia

    INDEX
    Explanations

    member and membership contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sufrido
    0.44
    𢎞
    0.43
     постра
    0.42
     Sebasti
    0.39
    ارق
    0.38
     Alonzo
    0.38
     carri
    0.38
     Maxim
    0.38
     elimin
    0.37
    Minimize
    0.37
    POSITIVE LOGITS
     Member
    0.46
     Membership
    0.45
    Membership
    0.43
    Member
    0.43
    getChildren
    0.43
    hips
    0.42
     membership
    0.41
    list
    0.40
    noch
    0.40
    ip
    0.40
    Act Density 0.003%

    No Known Activations