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

    Neuronpedia

    INDEX
    Explanations

    some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puisque
    0.50
    anden
    0.45
    ulle
    0.44
    whatever
    0.44
    Suitable
    0.44
    ustainability
    0.43
    punkt
    0.43
    annya
    0.43
     whatever
    0.42
    ensatz
    0.42
    POSITIVE LOGITS
     بعض
    1.06
     некоторые
    1.05
     algunos
    1.02
     برخی
    1.02
     некоторых
    0.99
     alguns
    0.99
     sommige
    0.96
     някои
    0.94
     some
    0.90
     ചില
    0.88
    Act Density 0.176%

    No Known Activations