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

    Neuronpedia

    INDEX
    Explanations

    writing style, vocabulary, grammar, tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rigidbody
    0.44
     multiuser
    0.42
    preliquidacion
    0.39
     rigged
    0.38
     headquartered
    0.38
     contrace
    0.37
     mainframe
    0.37
     hassle
    0.37
     baseApiPath
    0.36
     interoper
    0.36
    POSITIVE LOGITS
     vocabulary
    1.15
     stylistic
    1.05
     tone
    1.03
     phrasing
    1.02
     language
    0.97
     rhetorical
    0.97
     Vocabulary
    0.97
    语气
    0.96
     grammatical
    0.93
     punctuation
    0.93
    Act Density 0.122%

    No Known Activations