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

    Neuronpedia

    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hi
    0.68
     Shill
    0.66
     সাম্প্রদায়িক
    0.64
    ള്‍
    0.63
    ともに
    0.63
     रहीं
    0.61
    ꪽ
    0.60
     হইল
    0.59
    UIntValue
    0.59
    *;
    0.57
    POSITIVE LOGITS
     ?
    0.93
     Edward
    0.92
    9
    0.91
     CED
    0.89
     !!!
    0.88
     애
    0.87
    .(
    0.87
    8
    0.86
     Medal
    0.86
    ?(
    0.85
    Act Density 0.098%

    No Known Activations