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

    Neuronpedia

    INDEX
    Explanations

    argument and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nom
    0.76
    Nom
    0.74
     wording
    0.70
     diferenciales
    0.70
    Azure
    0.70
     entity
    0.66
     terminology
    0.66
    Executives
    0.65
    ക്ടര്‍
    0.64
     Entity
    0.64
    POSITIVE LOGITS
     persuasive
    1.72
     argumentative
    1.70
     persu
    1.44
     Argument
    1.40
     rhetorical
    1.39
     persuasion
    1.38
     persuade
    1.38
    Argument
    1.34
     argumentation
    1.33
     Rhet
    1.32
    Act Density 0.266%

    No Known Activations