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

    Neuronpedia

    INDEX
    Explanations

    assigning values and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     م
    0.68
     #
    0.66
     ن
    0.66
     -
    0.64
     נ
    0.64
     <
    0.62
     من
    0.55
     ;
    0.55
     с
    0.55
    ;
    0.54
    POSITIVE LOGITS
    𒊩
    1.18
    <unused1764>
    1.17
    𒂍
    1.17
    <unused534>
    1.17
    <unused127>
    1.16
    <unused1637>
    1.16
    𒇽
    1.15
    𒀉
    1.15
    <unused988>
    1.14
    <unused1965>
    1.14
    Act Density 0.164%

    No Known Activations