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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     behavior
    1.11
     മനസ്സ
    1.01
     hiyo
    1.00
     coscienza
    0.98
     asymptotically
    0.97
     contag
    0.97
    behavior
    0.97
     keseluruhan
    0.96
     contaminación
    0.96
     consequences
    0.95
    POSITIVE LOGITS
     N
    1.11
     מי
    1.10
     T
    1.06
     וש
    1.05
     G
    1.05
    anthemum
    1.04
     F
    1.04
    ek
    1.04
    Ch
    1.01
     Y
    0.99
    Act Density 0.499%

    No Known Activations