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

    Neuronpedia

    INDEX
    Explanations

    or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    任何
    0.45
     quelconque
    0.41
     інших
    0.40
     любого
    0.40
    कोई
    0.40
     any
    0.39
     cualquier
    0.39
     навіть
    0.39
     broader
    0.38
     quelcon
    0.38
    POSITIVE LOGITS
     it
    0.58
     they
    0.53
    they
    0.49
     It
    0.41
     THEY
    0.40
    iser
    0.39
    It
    0.38
     They
    0.38
     ĝi
    0.37
     вони
    0.36
    Act Density 0.017%

    No Known Activations