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

    Neuronpedia

    INDEX
    Explanations

    "between a" or "to a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ுங்கள்
    0.33
    ｪ
    0.33
     etiam
    0.26
     से
    0.26
    ത്തിലും
    0.26
    氓
    0.26
    학과
    0.26
     Ayrıca
    0.26
    학
    0.26
     refund
    0.25
    POSITIVE LOGITS
    taining
    0.35
    tained
    0.33
    the
    0.32
    drawn
    0.31
    ፍተኛ
    0.30
    transformed
    0.30
    theless
    0.29
    dut
    0.29
     dépens
    0.29
     menschen
    0.28
    Act Density 0.406%

    No Known Activations