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

    Neuronpedia

    INDEX
    Explanations

    paved roads and cobblestone streets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ።
    0.58
    ။
    0.53
     იაპ
    0.51
    ोनेशिया
    0.50
    ។
    0.50
     wich
    0.49
     الايه
    0.49
     perspiration
    0.47
    ќ
    0.47
     하나님
    0.47
    POSITIVE LOGITS
     trăm
    0.52
    ಕ
    0.52
    बी
    0.50
    <0x8F>
    0.49
    lerinden
    0.49
     μόνο
    0.48
    編
    0.48
    จาก
    0.47
    का
    0.47
    يز
    0.47
    Act Density 0.031%

    No Known Activations