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

    Neuronpedia

    INDEX
    Explanations

    inserting/removing objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cater
    -0.09
     founders
    -0.08
    788
    -0.08
     waterfalls
    -0.08
     dance
    -0.07
     collectiv
    -0.07
     romant
    -0.07
     reachable
    -0.07
     tantra
    -0.07
     Pasadena
    -0.07
    POSITIVE LOGITS
    sertion
    0.14
    Insertion
    0.13
     દાખ
    0.12
     inserir
    0.12
     넣
    0.12
    _insert
    0.12
     insertar
    0.12
    .insert
    0.12
    	insert
    0.12
    (insert
    0.12
    Act Density 0.053%

    No Known Activations