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

    Neuronpedia

    INDEX
    Explanations

    systems of equations and inequalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.51
     Во
    0.49
     water
    0.47
     devotion
    0.47
    水
    0.46
     deposition
    0.46
    া
    0.45
     trips
    0.43
     rifle
    0.42
    a
    0.42
    POSITIVE LOGITS
    <unused260>
    0.47
    anyahu
    0.46
    >{</
    0.45
    >¯</
    0.45
     _$_
    0.45
    冴
    0.45
    cule
    0.44
     behaves
    0.44
     بشكل
    0.43
    kq
    0.43
    Act Density 0.000%

    No Known Activations