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

    Neuronpedia

    INDEX
    Explanations

    the act of judging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    1.09
    PUBLIC
    1.02
    public
    1.01
    พี
    0.99
    ORIG
    0.97
    PTR
    0.96
    !<
    0.96
    <b>
    0.96
    แน่นอน
    0.95
    <!
    0.95
    POSITIVE LOGITS
     oznacza
    1.25
     zorgt
    1.22
     Dieser
    1.21
     fornece
    1.19
     একইভাবে
    1.19
     umfasst
    1.18
    ρου
    1.18
     gives
    1.18
     darum
    1.18
     provides
    1.17
    Act Density 0.054%

    No Known Activations