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

    Neuronpedia

    INDEX
    Explanations

    math algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sd
    -0.06
    找到
    -0.06
     Widow
    -0.06
    Steve
    -0.06
     drain
    -0.06
     Freed
    -0.06
    แทน
    -0.06
     DDR
    -0.06
    fad
    -0.06
    Zen
    -0.06
    POSITIVE LOGITS
    lásil
    0.07
     gorgeous
    0.06
    fails
    0.06
     BaseModel
    0.06
     Depending
    0.06
    사의
    0.06
    müş
    0.06
    subs
    0.06
     �
    0.06
     producto
    0.06
    Act Density 0.059%

    No Known Activations