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

    Neuronpedia

    INDEX
    Explanations

    closed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    δώ
    -0.06
     fing
    -0.06
    ETHER
    -0.06
    晶
    -0.06
    Inv
    -0.05
    ับการ
    -0.05
     Monaco
    -0.05
    .Conv
    -0.05
     txn
    -0.05
     viet
    -0.05
    POSITIVE LOGITS
    ellij
    0.07
     معل
    0.07
     Počet
    0.07
     crossing
    0.07
     blacklist
    0.06
     Rust
    0.06
     deletion
    0.06
    ﾆ
    0.06
     lar
    0.06
     köz
    0.06
    Act Density 0.026%

    No Known Activations