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

    Neuronpedia

    INDEX
    Explanations

    if clauses with pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CGA
    0.39
     LPA
    0.37
     spa
    0.37
     tore
    0.37
    ồng
    0.37
     pa
    0.36
     ABSORBED
    0.36
     foreseeable
    0.36
     PHA
    0.36
    ல்க
    0.36
    POSITIVE LOGITS
     they
    0.54
    Indeed
    0.48
     она
    0.47
     вона
    0.47
     вони
    0.46
    indeed
    0.46
     Indeed
    0.46
     it
    0.45
     они
    0.45
     indeed
    0.44
    Act Density 0.015%

    No Known Activations