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

    Neuronpedia

    INDEX
    Explanations

    the core idea/claim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     শ্রে
    0.49
     중요
    0.44
     vigt
    0.44
     miracles
    0.43
     hopelessly
    0.43
     éxito
    0.42
    优势
    0.41
    STRAL
    0.41
    Gap
    0.41
    解决了
    0.41
    POSITIVE LOGITS
     question
    0.62
     questione
    0.57
     argument
    0.57
     matter
    0.51
     issue
    0.51
     allegation
    0.50
     cuestión
    0.49
     ACLU
    0.47
     objection
    0.47
     accusation
    0.46
    Act Density 0.005%

    No Known Activations