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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bisa
    1.93
     could
    1.88
     can
    1.73
     dapat
    1.72
    could
    1.71
     يمكن
    1.70
     могат
    1.69
    Could
    1.68
     Could
    1.67
    สามารถ
    1.64
    POSITIVE LOGITS
     NEEDS
    0.61
    Needs
    0.59
     Needs
    0.58
     needs
    0.54
    needs
    0.51
    須
    0.48
    就需要
    0.46
    需
    0.45
    须
    0.44
    NEED
    0.44
    Act Density 0.029%

    No Known Activations