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

    Neuronpedia

    INDEX
    Explanations

    collective behavior, ants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.56
    рым
    0.49
    ের
    0.45
    े
    0.45
    트
    0.45
     ধান
    0.44
    لح
    0.43
    ی
    0.42
     Diario
    0.42
    璋
    0.42
    POSITIVE LOGITS
    ants
    0.53
    ying
    0.53
    astrophe
    0.52
    ama
    0.51
    with
    0.50
     singly
    0.48
    ies
    0.48
    ains
    0.48
    alam
    0.48
    K
    0.48
    Act Density 0.001%

    No Known Activations