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

    Neuronpedia

    INDEX
    Explanations

    titles and headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }^{+}
    0.43
     மண
    0.43
     पीड़ित
    0.43
    மண
    0.42
     tau
    0.39
     पीड़ित
    0.39
    atch
    0.39
    ISSION
    0.39
     ভূমি
    0.39
     INDUSTRIAL
    0.38
    POSITIVE LOGITS
    Title
    0.44
     title
    0.44
    Titulo
    0.40
    title
    0.39
    タイトル
    0.38
     Quintana
    0.38
     títulos
    0.38
     departe
    0.38
     titles
    0.37
    TITLE
    0.37
    Act Density 0.000%

    No Known Activations