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

    Neuronpedia

    INDEX
    Explanations

    stage directions/character introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    これからも
    0.81
     zusätzlich
    0.78
    下次
    0.78
     addUser
    0.78
     Ayrıca
    0.77
     additional
    0.76
     soov
    0.75
    กลับ
    0.75
     additionally
    0.75
     తిరిగి
    0.75
    POSITIVE LOGITS
     greeted
    1.78
     greets
    1.64
     greet
    1.52
     greeting
    1.41
     introductions
    1.37
     settling
    1.30
     greetings
    1.29
     introductory
    1.27
     begrü
    1.27
     introduction
    1.26
    Act Density 0.183%

    No Known Activations