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

    Neuronpedia

    INDEX
    Explanations

    purpose for future goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    0.77
    г
    0.76
    dk
    0.75
    te
    0.74
    umping
    0.73
    dut
    0.73
    فت
    0.72
     Beitrag
    0.72
    s
    0.71
     ရက်
    0.71
    POSITIVE LOGITS
     efforts
    0.77
     goals
    0.71
     equality
    0.70
     goal
    0.69
     excellence
    0.69
    И
    0.69
    目標
    0.68
    努力
    0.66
     mục
    0.66
    ίας
    0.63
    Act Density 0.232%

    No Known Activations