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

    Neuronpedia

    INDEX
    Explanations

    user prompts for input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interactivity
    0.41
    payers
    0.40
     زبان
    0.38
     Jerusal
    0.38
    שי
    0.37
    拉丁
    0.36
    لاه
    0.36
    गानिस्तान
    0.36
    activo
    0.36
    的应用
    0.36
    POSITIVE LOGITS
    What
    0.44
    Put
    0.43
     What
    0.43
     put
    0.42
    va
    0.42
     Caption
    0.41
     Provided
    0.40
    BTW
    0.40
    什么是
    0.38
    Did
    0.38
    Act Density 0.028%

    No Known Activations