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

    Neuronpedia

    INDEX
    Explanations

    expressing need or requirement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.58
     минус
    0.56
    urilor
    0.55
     overflowing
    0.54
     яку
    0.54
    ૦
    0.53
    рыма
    0.51
    ＮＡＮＡ
    0.50
     보이는
    0.50
    銷售
    0.49
    POSITIVE LOGITS
     to
    1.11
     need
    0.91
     필요
    0.76
     needed
    0.75
    Need
    0.75
     Need
    0.75
    need
    0.75
    Needed
    0.75
     behöver
    0.73
     dringend
    0.72
    Act Density 0.173%

    No Known Activations