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

    Neuronpedia

    INDEX
    Explanations

    training and upbringing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pihak
    1.57
    on
    1.37
    করণ
    1.32
    യായിരുന്നു
    1.31
     ETA
    1.31
     colloqu
    1.29
     Rio
    1.29
    র
    1.27
    枸
    1.26
     ingredient
    1.26
    POSITIVE LOGITS
    Acetoxy
    1.43
    vaient
    1.33
     helplessness
    1.28
     tume
    1.26
     convulsions
    1.24
    เคย
    1.20
    מס
    1.20
    ㎎
    1.19
     insults
    1.19
    ਲਾਂ
    1.19
    Act Density 0.272%

    No Known Activations