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

    Neuronpedia

    INDEX
    Explanations

    not interested or comfortable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]^
    0.48
     عامر
    0.44
    പ്പെടുന്നു
    0.41
    ^+$
    0.38
    НР
    0.38
    !`
    0.38
    城镇
    0.37
    xmax
    0.37
    پر
    0.37
    rlen
    0.37
    POSITIVE LOGITS
     expect
    0.65
     achieve
    0.54
     expects
    0.51
     achieves
    0.49
     focus
    0.48
    ach
    0.47
     want
    0.47
     ache
    0.46
     oček
    0.46
     obtain
    0.46
    Act Density 0.000%

    No Known Activations