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

    Neuronpedia

    INDEX
    Explanations

    those who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    These
    0.45
     These
    0.45
     zodat
    0.44
    these
    0.41
     queste
    0.39
     THESE
    0.39
    es
    0.39
             
    0.38
    er
    0.38
     mientras
    0.37
    POSITIVE LOGITS
     who
    0.71
     الذين
    0.65
     ktorí
    0.56
     którzy
    0.52
     kteří
    0.52
    jenigen
    0.49
     pesky
    0.47
     যারা
    0.45
     closest
    0.45
    who
    0.45
    Act Density 0.005%

    No Known Activations