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

    Neuronpedia

    INDEX
    Explanations

    Indian names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.76
     (
    0.68
     common
    0.67
       
    0.62
     a
    0.62
     *
    0.61
     imperative
    0.60
     essential
    0.60
     using
    0.58
     lowercase
    0.57
    POSITIVE LOGITS
    arrerol
    1.01
    nicheskij
    0.91
    ♍
    0.91
     senador
    0.88
    🚠
    0.86
    goài
    0.85
    🈯
    0.84
    asambhavam
    0.84
    atthakath
    0.84
    📪
    0.82
    Act Density 0.043%

    No Known Activations