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

    Neuronpedia

    INDEX
    Explanations

    sales, wind, AI, heavy silk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বিচার
    0.42
    ज़ा
    0.41
     $\{
    0.40
    ່າງ
    0.40
     شهری
    0.40
    આ
    0.40
     Rac
    0.39
     Azul
    0.39
     Ambiental
    0.39
    评
    0.39
    POSITIVE LOGITS
     gamanam
    0.40
     structs
    0.38
    rictions
    0.37
     waarvan
    0.37
     voul
    0.37
    ◹
    0.37
    gate
    0.36
    Ivan
    0.35
    Norman
    0.35
     डिल
    0.35
    Act Density 0.002%

    No Known Activations