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

    Neuronpedia

    INDEX
    Explanations

    apo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treasures
    -0.07
     Crystal
    -0.06
     Grammar
    -0.06
     Chunk
    -0.06
     Scanner
    -0.06
     Manhattan
    -0.06
     Cons
    -0.06
     embeddings
    -0.06
     detay
    -0.06
     Utf
    -0.06
    POSITIVE LOGITS
     keinen
    0.07
     reaches
    0.07
     옆
    0.06
     melakukan
    0.06
    Did
    0.06
    =tf
    0.06
    187
    0.06
     nam
    0.06
    .assertNull
    0.06
     povin
    0.06
    Act Density 0.002%

    No Known Activations