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

    Neuronpedia

    INDEX
    Explanations

    titles starting with prepositions or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yrıca
    0.59
    䀓
    0.56
    інки
    0.55
     गेंदबाज
    0.55
    ेंशियल
    0.55
    ുകൾ
    0.53
    btnInventory
    0.53
    ActionsForRule
    0.53
    欳
    0.53
    ټبال
    0.52
    POSITIVE LOGITS
     the
    0.59
    0.57
     The
    0.55
     S
    0.54
     a
    0.53
    7
    0.53
    5
    0.52
     In
    0.51
     in
    0.50
    -
    0.50
    Act Density 0.000%

    No Known Activations