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

    Neuronpedia

    INDEX
    Explanations

    actions happening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stark
    0.48
     v
    0.46
     check
    0.44
     rich
    0.44
     sings
    0.43
     full
    0.43
     expanded
    0.42
     spire
    0.42
     sing
    0.42
     predominant
    0.42
    POSITIVE LOGITS
     μπορούν
    0.48
     требуется
    0.45
     mogą
    0.45
     يمكن
    0.44
     kunnen
    0.43
     dibutuhkan
    0.43
     maaaring
    0.42
    ítható
    0.42
     могло
    0.42
     behö
    0.42
    Act Density 0.102%

    No Known Activations