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

    Neuronpedia

    INDEX
    Explanations

    Ferris wheel offering views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.67
     आपली
    0.63
    T
    0.63
    O
    0.60
     미
    0.59
    미
    0.56
    ラ
    0.56
    Ми
    0.55
    S
    0.55
    L
    0.55
    POSITIVE LOGITS
     Ferris
    0.74
    ন
    0.59
     Protein
    0.57
     poteva
    0.57
     অনেকটাই
    0.55
    }+\
    0.54
     cambiamenti
    0.54
    बर्ग
    0.54
     protein
    0.52
     ferns
    0.52
    Act Density 0.000%

    No Known Activations